Upload model via Fine-tune Assistant
Browse files- README.md +362 -0
- benchmark/adversarial_samples.csv +81 -0
- benchmark/benchmark_results.json +873 -0
- config.json +33 -0
- evaluation_results.json +25 -0
- label_config.json +17 -0
- model.safetensors +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +59 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
|
@@ -0,0 +1,362 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: tr
|
| 3 |
+
license: other
|
| 4 |
+
license_name: siriusai-premium-v1
|
| 5 |
+
license_link: LICENSE
|
| 6 |
+
tags:
|
| 7 |
+
- turkish
|
| 8 |
+
- text-classification
|
| 9 |
+
- bert
|
| 10 |
+
- nlp
|
| 11 |
+
- transformers
|
| 12 |
+
- siriusai
|
| 13 |
+
- production-ready
|
| 14 |
+
- enterprise
|
| 15 |
+
base_model: dbmdz/bert-base-turkish-uncased
|
| 16 |
+
datasets:
|
| 17 |
+
- custom
|
| 18 |
+
metrics:
|
| 19 |
+
- f1
|
| 20 |
+
- precision
|
| 21 |
+
- recall
|
| 22 |
+
- accuracy
|
| 23 |
+
- mcc
|
| 24 |
+
library_name: transformers
|
| 25 |
+
pipeline_tag: text-classification
|
| 26 |
+
model-index:
|
| 27 |
+
- name: turn-detector
|
| 28 |
+
results:
|
| 29 |
+
- task:
|
| 30 |
+
type: text-classification
|
| 31 |
+
name: Text Classification
|
| 32 |
+
metrics:
|
| 33 |
+
- type: f1
|
| 34 |
+
value: 0.9924276856095726
|
| 35 |
+
name: Macro F1
|
| 36 |
+
- type: mcc
|
| 37 |
+
value: 0.9848560799888242
|
| 38 |
+
---
|
| 39 |
+
|
| 40 |
+
# turn-detector - Turkish Text Classification Model
|
| 41 |
+
|
| 42 |
+
<p align="center">
|
| 43 |
+
<a href="https://huggingface.co/hayatiali/turn-detector"><img src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-turn--detector-yellow" alt="Hugging Face"></a>
|
| 44 |
+
<a href="https://huggingface.co/hayatiali/turn-detector"><img src="https://img.shields.io/badge/Model-Production%20Ready-brightgreen" alt="Production Ready"></a>
|
| 45 |
+
<img src="https://img.shields.io/badge/Language-Turkish-blue" alt="Turkish">
|
| 46 |
+
<img src="https://img.shields.io/badge/Task-Text%20Classification-orange" alt="Text Classification">
|
| 47 |
+
</p>
|
| 48 |
+
|
| 49 |
+
This model is designed for classifying Turkish text into different turn-taking categories in a conversation.
|
| 50 |
+
|
| 51 |
+
*Developed by SiriusAI Tech Brain Team*
|
| 52 |
+
|
| 53 |
+
---
|
| 54 |
+
|
| 55 |
+
## Mission
|
| 56 |
+
|
| 57 |
+
> **To enhance conversational AI by accurately detecting turn-taking dynamics in Turkish dialogues, enabling more natural and engaging interactions.**
|
| 58 |
+
|
| 59 |
+
The `turn-detector` model is capable of classifying responses in Turkish conversations into two distinct categories: **agent_response** and **backchannel**. This functionality is crucial for developing advanced voice assistants and dialogue systems that better understand human interactions. By leveraging the power of the `BertForSequenceClassification` architecture, the model achieves remarkable accuracy and reliability.
|
| 60 |
+
|
| 61 |
+
### Why This Model Matters
|
| 62 |
+
|
| 63 |
+
- **High Accuracy**: With an impressive accuracy of over 99%, this model ensures reliable classifications in real-world applications.
|
| 64 |
+
- **Enterprise-Grade Performance**: Designed for production use, it meets the stringent requirements of enterprise clients.
|
| 65 |
+
- **NLP Expertise**: Developed using state-of-the-art natural language processing techniques, it provides a competitive edge in understanding Turkish conversations.
|
| 66 |
+
- **Scalable Solution**: Easily integratable into existing systems, allowing for seamless deployment in various applications.
|
| 67 |
+
- **Robust Training**: Trained on a substantial dataset, ensuring its effectiveness across diverse conversational contexts.
|
| 68 |
+
|
| 69 |
+
---
|
| 70 |
+
|
| 71 |
+
## Model Overview
|
| 72 |
+
|
| 73 |
+
| Property | Value |
|
| 74 |
+
|----------|-------|
|
| 75 |
+
| **Architecture** | BertForSequenceClassification |
|
| 76 |
+
| **Base Model** | `dbmdz/bert-base-turkish-uncased` |
|
| 77 |
+
| **Task** | Text Classification |
|
| 78 |
+
| **Language** | Turkish (tr) |
|
| 79 |
+
| **Categories** | 2 labels |
|
| 80 |
+
| **Model Size** | ~110M parameters |
|
| 81 |
+
| **Inference Time** | ~10-15ms (GPU) / ~40-50ms (CPU) |
|
| 82 |
+
|
| 83 |
+
---
|
| 84 |
+
|
| 85 |
+
## Performance Metrics
|
| 86 |
+
|
| 87 |
+
### Final Evaluation Results
|
| 88 |
+
|
| 89 |
+
| Metric | Score | Description |
|
| 90 |
+
|--------|-------|-------------|
|
| 91 |
+
| **Macro F1** | **0.9924** | Harmonic mean of precision and recall |
|
| 92 |
+
| **MCC** | **0.9849** | Matthews Correlation Coefficient |
|
| 93 |
+
| **Accuracy** | **99.3242%** | Ratio of correctly predicted instances to total instances |
|
| 94 |
+
|
| 95 |
+
### Per-Class Performance
|
| 96 |
+
|
| 97 |
+
| Category | Accuracy | Correct | Total |
|
| 98 |
+
|----------|----------|---------|-------|
|
| 99 |
+
| **agent_response** | 99.5% | 7,429 | 7,464 |
|
| 100 |
+
| **backchannel** | 98.9% | 3,741 | 3,782 |
|
| 101 |
+
|
| 102 |
+
---
|
| 103 |
+
|
| 104 |
+
## Dataset
|
| 105 |
+
|
| 106 |
+
### Dataset Statistics
|
| 107 |
+
|
| 108 |
+
| Split | Samples | Purpose |
|
| 109 |
+
|-------|---------|---------|
|
| 110 |
+
| **Train** | 44,982 | Model training |
|
| 111 |
+
| **Test** | 11,246 | Model evaluation |
|
| 112 |
+
| **Total** | 56,228 | Complete dataset |
|
| 113 |
+
|
| 114 |
+
### Category Distribution
|
| 115 |
+
|
| 116 |
+
| Category | Samples | Percentage | Description |
|
| 117 |
+
|----------|---------|------------|-------------|
|
| 118 |
+
| **turn_action** | 56,228 | 100.0% | turn_action category |
|
| 119 |
+
|
| 120 |
+
### Subcategory Breakdown
|
| 121 |
+
|
| 122 |
+
| Category | Subcategories |
|
| 123 |
+
|----------|---------------|
|
| 124 |
+
| **turn_action** | agent_response, backchannel |
|
| 125 |
+
|
| 126 |
+
---
|
| 127 |
+
|
| 128 |
+
## Label Definitions
|
| 129 |
+
|
| 130 |
+
| Label | ID | Description | Turkish Examples |
|
| 131 |
+
|-------|-----|-------------|------------------|
|
| 132 |
+
| **agent_response** | 0 | Represents a direct response from the agent in a conversation | "Merhaba, size nasıl yardımcı olabilirim?" |
|
| 133 |
+
| **backchannel** | 1 | Indicates acknowledgment or encouragement from the listener | "Evet", "Anladım" |
|
| 134 |
+
|
| 135 |
+
### Important: Category Boundaries
|
| 136 |
+
|
| 137 |
+
The distinction between **agent_response** and **backchannel** is critical. An **agent_response** represents a substantive reply to a query, while **backchannel** responses are brief acknowledgments that do not provide new information.
|
| 138 |
+
|
| 139 |
+
---
|
| 140 |
+
|
| 141 |
+
## Training Procedure
|
| 142 |
+
|
| 143 |
+
### Hyperparameters
|
| 144 |
+
|
| 145 |
+
| Parameter | Value |
|
| 146 |
+
|-----------|-------|
|
| 147 |
+
| **Base Model** | `dbmdz/bert-base-turkish-uncased` |
|
| 148 |
+
| **Max Sequence Length** | 128 tokens |
|
| 149 |
+
| **Batch Size** | 16 |
|
| 150 |
+
| **Learning Rate** | 2e-5 |
|
| 151 |
+
| **Epochs** | 3 |
|
| 152 |
+
| **Optimizer** | AdamW |
|
| 153 |
+
| **Weight Decay** | 0.01 |
|
| 154 |
+
| **Loss Function** | CrossEntropyLoss / Focal Loss |
|
| 155 |
+
| **Problem Type** | Single-label / Multi-label Classification |
|
| 156 |
+
|
| 157 |
+
### Training Environment
|
| 158 |
+
|
| 159 |
+
| Resource | Specification |
|
| 160 |
+
|----------|---------------|
|
| 161 |
+
| **Hardware** | Apple Silicon (MPS) / CUDA GPU |
|
| 162 |
+
| **Framework** | PyTorch + Transformers |
|
| 163 |
+
| **Training Time** | Varies based on dataset size |
|
| 164 |
+
|
| 165 |
+
---
|
| 166 |
+
|
| 167 |
+
## Usage
|
| 168 |
+
|
| 169 |
+
### Installation
|
| 170 |
+
|
| 171 |
+
```bash
|
| 172 |
+
pip install transformers torch
|
| 173 |
+
```
|
| 174 |
+
|
| 175 |
+
### Quick Start
|
| 176 |
+
|
| 177 |
+
```python
|
| 178 |
+
from transformers import AutoTokenizer, AutoModelForSequenceClassification
|
| 179 |
+
import torch
|
| 180 |
+
|
| 181 |
+
model_name = "hayatiali/turn-detector"
|
| 182 |
+
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
| 183 |
+
model = AutoModelForSequenceClassification.from_pretrained(model_name)
|
| 184 |
+
model.eval()
|
| 185 |
+
|
| 186 |
+
LABELS = ["agent_response", "backchannel"]
|
| 187 |
+
|
| 188 |
+
def predict(text):
|
| 189 |
+
inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=128)
|
| 190 |
+
with torch.no_grad():
|
| 191 |
+
outputs = model(**inputs)
|
| 192 |
+
probs = torch.softmax(outputs.logits, dim=-1)[0]
|
| 193 |
+
|
| 194 |
+
scores = {label: float(prob) for label, prob in zip(LABELS, probs)}
|
| 195 |
+
primary = max(scores, key=scores.get)
|
| 196 |
+
return {"category": primary, "confidence": scores[primary], "all_scores": scores}
|
| 197 |
+
|
| 198 |
+
# Examples
|
| 199 |
+
print(predict("Merhaba, nasılsınız?"))
|
| 200 |
+
```
|
| 201 |
+
|
| 202 |
+
### Production Class
|
| 203 |
+
|
| 204 |
+
```python
|
| 205 |
+
class TurnDetectorClassifier:
|
| 206 |
+
LABELS = ["agent_response", "backchannel"]
|
| 207 |
+
|
| 208 |
+
def __init__(self, model_path="hayatiali/turn-detector"):
|
| 209 |
+
self.tokenizer = AutoTokenizer.from_pretrained(model_path)
|
| 210 |
+
self.model = AutoModelForSequenceClassification.from_pretrained(model_path)
|
| 211 |
+
self.device = "cuda" if torch.cuda.is_available() else "cpu"
|
| 212 |
+
self.model.to(self.device).eval()
|
| 213 |
+
|
| 214 |
+
def predict(self, text: str) -> dict:
|
| 215 |
+
inputs = self.tokenizer(text, return_tensors="pt", truncation=True, max_length=128)
|
| 216 |
+
inputs = {k: v.to(self.device) for k, v in inputs.items()}
|
| 217 |
+
|
| 218 |
+
with torch.no_grad():
|
| 219 |
+
logits = self.model(**inputs).logits
|
| 220 |
+
probs = torch.softmax(logits, dim=-1)[0].cpu().numpy()
|
| 221 |
+
|
| 222 |
+
scores = dict(zip(self.LABELS, probs))
|
| 223 |
+
return {"category": max(scores, key=scores.get), "confidence": max(scores.values()), "scores": scores}
|
| 224 |
+
```
|
| 225 |
+
|
| 226 |
+
### Batch Inference
|
| 227 |
+
|
| 228 |
+
```python
|
| 229 |
+
def predict_batch(texts: list, batch_size: int = 32) -> list:
|
| 230 |
+
results = []
|
| 231 |
+
for i in range(0, len(texts), batch_size):
|
| 232 |
+
batch = texts[i:i + batch_size]
|
| 233 |
+
inputs = tokenizer(batch, return_tensors="pt", truncation=True, max_length=128, padding=True)
|
| 234 |
+
inputs = {k: v.to(device) for k, v in inputs.items()}
|
| 235 |
+
|
| 236 |
+
with torch.no_grad():
|
| 237 |
+
probs = torch.softmax(model(**inputs).logits, dim=-1).cpu().numpy()
|
| 238 |
+
|
| 239 |
+
for prob in probs:
|
| 240 |
+
scores = dict(zip(LABELS, prob))
|
| 241 |
+
results.append(scores)
|
| 242 |
+
return results
|
| 243 |
+
```
|
| 244 |
+
|
| 245 |
+
---
|
| 246 |
+
|
| 247 |
+
## Limitations & Known Issues
|
| 248 |
+
|
| 249 |
+
### ⚠️ Model Limitations
|
| 250 |
+
|
| 251 |
+
| Limitation | Details | Impact |
|
| 252 |
+
|------------|---------|--------|
|
| 253 |
+
| **Dataset Bias** | Model performance may vary on conversational data outside the training set. | Could lead to inaccuracies in specific domains. |
|
| 254 |
+
| **Language Nuance** | Captures standard Turkish but may struggle with dialects or highly informal speech. | Reduced accuracy in non-standard language use. |
|
| 255 |
+
| **Context Understanding** | Limited ability to understand context beyond single-turn interactions. | May misclassify responses that rely on previous context. |
|
| 256 |
+
|
| 257 |
+
### ⚠️ Production Deployment Considerations
|
| 258 |
+
|
| 259 |
+
| Consideration | Details | Recommendation |
|
| 260 |
+
|---------------|---------|----------------|
|
| 261 |
+
| **Model Size** | Large model size may impact deployment on limited-resource environments. | Consider model distillation or quantization for constrained environments. |
|
| 262 |
+
|
| 263 |
+
### Not Suitable For
|
| 264 |
+
|
| 265 |
+
- Real-time critical applications without human oversight.
|
| 266 |
+
- Scenarios requiring high levels of contextual understanding across multiple turns.
|
| 267 |
+
- Use cases in non-Turkish languages without adaptation.
|
| 268 |
+
|
| 269 |
+
---
|
| 270 |
+
|
| 271 |
+
## Ethical Considerations
|
| 272 |
+
|
| 273 |
+
### Intended Use
|
| 274 |
+
|
| 275 |
+
- Conversational AI applications.
|
| 276 |
+
- Voice assistants and chatbots.
|
| 277 |
+
- Customer service automation.
|
| 278 |
+
|
| 279 |
+
### Risks
|
| 280 |
+
|
| 281 |
+
- **Bias in Training Data**: If the training data is biased, the model may perpetuate those biases in its predictions.
|
| 282 |
+
- **Misuse of Technology**: Potential for the model to be used in contexts that require ethical considerations, such as surveillance or deceptive practices.
|
| 283 |
+
|
| 284 |
+
### Recommendations
|
| 285 |
+
|
| 286 |
+
1. **Human Oversight**: Always implement human oversight in applications that utilize the model.
|
| 287 |
+
2. **Monitoring**: Continuously monitor model outputs for unexpected or biased behavior.
|
| 288 |
+
3. **Updates**: Regularly update the model with new data to improve accuracy and mitigate biases.
|
| 289 |
+
|
| 290 |
+
---
|
| 291 |
+
|
| 292 |
+
## Technical Specifications
|
| 293 |
+
|
| 294 |
+
### Model Architecture
|
| 295 |
+
|
| 296 |
+
```
|
| 297 |
+
BertForSequenceClassification(
|
| 298 |
+
(bert): BertModel(
|
| 299 |
+
(embeddings): BertEmbeddings
|
| 300 |
+
(encoder): BertEncoder (12 layers)
|
| 301 |
+
(pooler): BertPooler
|
| 302 |
+
)
|
| 303 |
+
(dropout): Dropout(p=0.1)
|
| 304 |
+
(classifier): Linear(in_features=768, out_features=2)
|
| 305 |
+
)
|
| 306 |
+
|
| 307 |
+
Total Parameters: ~110M
|
| 308 |
+
```
|
| 309 |
+
|
| 310 |
+
### Input/Output
|
| 311 |
+
|
| 312 |
+
- **Input**: Turkish text (max 128 tokens)
|
| 313 |
+
- **Output**: 2-dimensional probability vector
|
| 314 |
+
- **Tokenizer**: BERTurk WordPiece (32k vocab)
|
| 315 |
+
|
| 316 |
+
---
|
| 317 |
+
|
| 318 |
+
## Citation
|
| 319 |
+
|
| 320 |
+
```bibtex
|
| 321 |
+
@misc{turn-detector-2025,
|
| 322 |
+
title={turn-detector - Turkish Text Classification Model},
|
| 323 |
+
author={SiriusAI Tech Brain Team},
|
| 324 |
+
year={2025},
|
| 325 |
+
publisher={Hugging Face},
|
| 326 |
+
howpublished={\url{https://huggingface.co/hayatiali/turn-detector}},
|
| 327 |
+
note={Fine-tuned from dbmdz/bert-base-turkish-uncased}
|
| 328 |
+
}
|
| 329 |
+
```
|
| 330 |
+
|
| 331 |
+
---
|
| 332 |
+
|
| 333 |
+
## Model Card Authors
|
| 334 |
+
|
| 335 |
+
**SiriusAI Tech Brain Team**
|
| 336 |
+
|
| 337 |
+
## Contact
|
| 338 |
+
|
| 339 |
+
- **Email**: info@siriusaitech.com
|
| 340 |
+
- **Repository**: [GitHub](https://github.com/sirius-tedarik)
|
| 341 |
+
|
| 342 |
+
---
|
| 343 |
+
|
| 344 |
+
## Changelog
|
| 345 |
+
|
| 346 |
+
### v1.0 (Current)
|
| 347 |
+
- Initial release
|
| 348 |
+
- 2-category text classification
|
| 349 |
+
- Macro F1: 0.9924, MCC: 0.9849
|
| 350 |
+
|
| 351 |
+
---
|
| 352 |
+
|
| 353 |
+
**License**: SiriusAI Tech Premium License v1.0
|
| 354 |
+
|
| 355 |
+
**Commercial Use**: Requires Premium License. Contact: info@siriusaitech.com
|
| 356 |
+
|
| 357 |
+
**Free Use Allowed For**:
|
| 358 |
+
- Academic research and education
|
| 359 |
+
- Non-profit organizations (with approval)
|
| 360 |
+
- Evaluation (30 days)
|
| 361 |
+
|
| 362 |
+
**Disclaimer**: This model is designed for text classification applications. Always implement with appropriate safeguards and human oversight. Model predictions should inform decisions, not replace human judgment.
|
benchmark/adversarial_samples.csv
ADDED
|
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
text,expected_label,predicted_label,difficulty,confidence,is_correct
|
| 2 |
+
"Ömer, nasıl yardımcı olabilirim?",agent_response,agent_response,baseline,0.8812354207038879,True
|
| 3 |
+
"Merhaba, hangi konuda yardım edebilirim?",agent_response,agent_response,baseline,0.9911393523216248,True
|
| 4 |
+
"Tabii ki, size bununla ilgili bilgi verebilirim.",agent_response,agent_response,baseline,0.5156869292259216,True
|
| 5 |
+
"Elbette, bu konuda size destek olacağım.",agent_response,backchannel,baseline,0.5563545823097229,False
|
| 6 |
+
"Anladım, hemen kontrol ediyorum.",agent_response,backchannel,baseline,0.5459677577018738,False
|
| 7 |
+
"Lütfen bekleyin, birazdan yanıt vereceğim.",agent_response,agent_response,baseline,0.8637070655822754,True
|
| 8 |
+
Bu konuda yardımcı olmaktan memnuniyet duyarım.,agent_response,agent_response,baseline,0.6278860569000244,True
|
| 9 |
+
Hemen sizin için araştırıyorum.,agent_response,agent_response,baseline,0.7357267737388611,True
|
| 10 |
+
"Endişelenmeyin, bu konuyu halledeceğiz.",agent_response,agent_response,baseline,0.6491527557373047,True
|
| 11 |
+
"Herhangi başka bir sorunuz varsa, sormaktan çekinmeyin.",agent_response,agent_response,baseline,0.9041098952293396,True
|
| 12 |
+
totes agree lol,agent_response,backchannel,length_noise,0.9879427552223206,False
|
| 13 |
+
yup yup yup yup yup,agent_response,backchannel,length_noise,0.988431453704834,False
|
| 14 |
+
"OMG cant believe u did that, like seriously, i mean come on, its just too much, you know what i mean? cuz if you dont then idk what to say, like seriously",agent_response,agent_response,length_noise,0.909318745136261,True
|
| 15 |
+
nah bro,agent_response,backchannel,length_noise,0.9873980283737183,False
|
| 16 |
+
yasss that's wassup,agent_response,backchannel,length_noise,0.974721372127533,False
|
| 17 |
+
okay okay okay i get it already no need to repeat urself over and over again like i'm not deaf or whatever,agent_response,agent_response,length_noise,0.9450967907905579,True
|
| 18 |
+
omg thts crazee,agent_response,backchannel,length_noise,0.9885514974594116,False
|
| 19 |
+
u r kidding right?,agent_response,backchannel,length_noise,0.9817968606948853,False
|
| 20 |
+
"wow just wow, i mean, wow! i never thought that this would happen, like ever, not in a million years, and yet here we are, unbelievable, just totally unbelievable, you feel me?",agent_response,agent_response,length_noise,0.8823995590209961,True
|
| 21 |
+
hah lol whatevs,agent_response,backchannel,length_noise,0.9895368814468384,False
|
| 22 |
+
"Ah, anlıyorum. Devam edebilir misiniz?",agent_response,agent_response,semantic_overlap,0.8250168561935425,True
|
| 23 |
+
"Hmm, bunu biraz daha açabilir misiniz?",agent_response,agent_response,semantic_overlap,0.745111882686615,True
|
| 24 |
+
"Evet, bu gerçekten ilginç. Daha fazla bilgi verebilir misiniz?",agent_response,agent_response,semantic_overlap,0.9849535226821899,True
|
| 25 |
+
Bu konuda düşündüğünüz başka bir şey var mı?,agent_response,agent_response,semantic_overlap,0.9519035220146179,True
|
| 26 |
+
"Hımm, pekala. Başka bir açıdan bakacak olursak?",agent_response,backchannel,semantic_overlap,0.903683066368103,False
|
| 27 |
+
"Evet, kesinlikle. Peki başka hangi yönlerini ele alabiliriz?",agent_response,agent_response,semantic_overlap,0.9927364587783813,True
|
| 28 |
+
"Tamam, peki buna ek olarak ne söyleyebilirsiniz?",agent_response,agent_response,semantic_overlap,0.9534065127372742,True
|
| 29 |
+
"Anladım, devam etmek ister misiniz?",agent_response,agent_response,semantic_overlap,0.974102795124054,True
|
| 30 |
+
"Evet, peki başka bir detaya dikkat çekmek ister misiniz?",agent_response,agent_response,semantic_overlap,0.9879535436630249,True
|
| 31 |
+
"Hmm, çok iyi bir nokta. Bunu biraz daha açar mısınız?",agent_response,agent_response,semantic_overlap,0.9757851362228394,True
|
| 32 |
+
"Oh great, another software update that will surely make everything run faster, just like last time.",agent_response,agent_response,edge_cases,0.895721971988678,True
|
| 33 |
+
"I'm sure the server downtime at exactly 5 PM on a Friday was purely coincidental, and not at all inconvenient.",agent_response,agent_response,edge_cases,0.849263072013855,True
|
| 34 |
+
"Yeah, because deleting the database with a single command is exactly what everyone wants, right?",agent_response,agent_response,edge_cases,0.7744247317314148,True
|
| 35 |
+
"I just love it when my AI assistant corrects me even when I'm right, it's like having a personal grammar teacher.",agent_response,agent_response,edge_cases,0.5396984815597534,True
|
| 36 |
+
"No, I absolutely don't need any more disk space. Who needs to store files anyway?",agent_response,agent_response,edge_cases,0.9811112284660339,True
|
| 37 |
+
"Sure, let's implement the new feature without any testing. What could possibly go wrong?",agent_response,agent_response,edge_cases,0.9612233638763428,True
|
| 38 |
+
"Oh, another meeting about meetings? This is exactly why I got into tech.",agent_response,agent_response,edge_cases,0.9544288516044617,True
|
| 39 |
+
I'm really looking forward to debugging this code at 2 AM again. It's the highlight of my week.,agent_response,agent_response,edge_cases,0.8809834122657776,True
|
| 40 |
+
The best part of working with AI is when it confidently gives you the wrong answer.,agent_response,agent_response,edge_cases,0.8558328151702881,True
|
| 41 |
+
"Of course, let’s deploy the untested code on a Friday evening, I have nothing better to do.",agent_response,agent_response,edge_cases,0.7736720442771912,True
|
| 42 |
+
"Evet, seni anlıyorum.",backchannel,backchannel,baseline,0.8567759990692139,True
|
| 43 |
+
"Hmm, ilginç.",backchannel,backchannel,baseline,0.985055685043335,True
|
| 44 |
+
"Evet, devam et.",backchannel,backchannel,baseline,0.8956389427185059,True
|
| 45 |
+
Gerçekten mi?,backchannel,backchannel,baseline,0.9868144989013672,True
|
| 46 |
+
"Tamam, bu mantıklı.",backchannel,backchannel,baseline,0.7614496946334839,True
|
| 47 |
+
Anladım.,backchannel,backchannel,baseline,0.9884626269340515,True
|
| 48 |
+
"Evet, bu doğru.",backchannel,backchannel,baseline,0.8082573413848877,True
|
| 49 |
+
"Ah, şimdi anlıyorum.",backchannel,backchannel,baseline,0.9578026533126831,True
|
| 50 |
+
Bu ilginç bir nokta.,backchannel,backchannel,baseline,0.6748051643371582,True
|
| 51 |
+
"Evet, buna katılıyorum.",backchannel,backchannel,baseline,0.8088875412940979,True
|
| 52 |
+
yaaaa broooo,backchannel,backchannel,length_noise,0.9909811615943909,True
|
| 53 |
+
huh? r u srz??,backchannel,backchannel,length_noise,0.9855925440788269,True
|
| 54 |
+
OMG this is like the most amazing thing ever I mean I can't even begin to explain how incredible this whole situation is because it's just that awesome you know what I mean like seriously wow just wow ok???,backchannel,agent_response,length_noise,0.7402034997940063,False
|
| 55 |
+
idk wat u mean,backchannel,backchannel,length_noise,0.9897193908691406,True
|
| 56 |
+
sure sure sure sure sure,backchannel,backchannel,length_noise,0.9763302206993103,True
|
| 57 |
+
omg totally 100% agree with you on that one no doubt about it in fact I was just thinking the same thing the other day and it's crazy how we're like on the same wavelength all the time isn't it?,backchannel,agent_response,length_noise,0.9482101798057556,False
|
| 58 |
+
no wayyyy,backchannel,backchannel,length_noise,0.991447925567627,True
|
| 59 |
+
"heyyy, u ther?",backchannel,backchannel,length_noise,0.990699827671051,True
|
| 60 |
+
wow cant believe it happened like that i mean who would have thought that everything would turn out this way after all the planning we did it just goes to show that sometimes things have a way of working out on their own despite all the odds and challenges we faced right from the start,backchannel,agent_response,length_noise,0.971515953540802,False
|
| 61 |
+
kk thx bye,backchannel,backchannel,length_noise,0.99072265625,True
|
| 62 |
+
"Hmm, ilginç bir nokta.",backchannel,backchannel,semantic_overlap,0.9318225979804993,True
|
| 63 |
+
"Anladım, peki ya sonra?",backchannel,backchannel,semantic_overlap,0.9160572290420532,True
|
| 64 |
+
"Hmm, o konuda biraz daha bilgi verir misin?",backchannel,agent_response,semantic_overlap,0.7073332667350769,False
|
| 65 |
+
Gerçekten mi? Daha fazla duymak isterim.,backchannel,backchannel,semantic_overlap,0.7160800099372864,True
|
| 66 |
+
"Bu mantıklı, başka neler oldu?",backchannel,agent_response,semantic_overlap,0.812181293964386,False
|
| 67 |
+
"Hmm, bunu daha önce duymamıştım.",backchannel,backchannel,semantic_overlap,0.8978190422058105,True
|
| 68 |
+
"Bir dakika, bunu doğru mu anlıyorum?",backchannel,agent_response,semantic_overlap,0.7696111798286438,False
|
| 69 |
+
"Peki, sonra ne yaptılar?",backchannel,backchannel,semantic_overlap,0.6477120518684387,True
|
| 70 |
+
Gerçekten mi? Bu beni düşündürdü.,backchannel,backchannel,semantic_overlap,0.9161955714225769,True
|
| 71 |
+
"İlginç, devam et lütfen.",backchannel,backchannel,semantic_overlap,0.7439655661582947,True
|
| 72 |
+
"Evet evet, tabii ki de tebrik ederim, dünya harikası bir iş çıkardın (!)",backchannel,agent_response,edge_cases,0.877510666847229,False
|
| 73 |
+
"Çok güzel, bu kadar net bir çözüm bulduğunu(!) hiç düşünmemiştim doğrusu.",backchannel,agent_response,edge_cases,0.9826798439025879,False
|
| 74 |
+
"Ah, tabii ki! Çünkü herkes daima müşteri hizmetlerinin ne kadar hızlı olduğunu söyler (!)",backchannel,agent_response,edge_cases,0.5608082413673401,False
|
| 75 |
+
"Eğer bu kadar 'yaratıcı' bir fikir daha duyar mıyım diye düşünüyordum, teşekkürler!",backchannel,agent_response,edge_cases,0.9653686881065369,False
|
| 76 |
+
Bir işin en iyi nasıl yapılmaması gerektiğini görmek için harika (!) bir örnekti.,backchannel,agent_response,edge_cases,0.9630967378616333,False
|
| 77 |
+
"Evet, kesinlikle bugünkü toplantıda hiçbir şey anlaşılmadı diyemem.",backchannel,agent_response,edge_cases,0.8947334289550781,False
|
| 78 |
+
"Harika, seninki gibi bir çözüm sayesinde sorunlarımız iki katına çıkacak (!)",backchannel,agent_response,edge_cases,0.8286226987838745,False
|
| 79 |
+
"Tabii ki de, Türk çayı yurt dışında sudan bile ucuzdur (!).",backchannel,backchannel,edge_cases,0.8883209228515625,True
|
| 80 |
+
"Bu kadar ‘detaylı’ bir analiz için üç cümle yeterli oldu, harikasın!",backchannel,agent_response,edge_cases,0.610821545124054,False
|
| 81 |
+
"Elbette, herkesin sabırsızlıkla beklediği o 'harika' PowerPoint sunumunu bir daha görelim.",backchannel,agent_response,edge_cases,0.9590893387794495,False
|
benchmark/benchmark_results.json
ADDED
|
@@ -0,0 +1,873 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_name": "turn-detector",
|
| 3 |
+
"generated_at": "2025-12-14T21:37:22.477273",
|
| 4 |
+
"difficulty_results": {
|
| 5 |
+
"baseline": {
|
| 6 |
+
"total": 20,
|
| 7 |
+
"correct": 18,
|
| 8 |
+
"accuracy": 0.9
|
| 9 |
+
},
|
| 10 |
+
"length_noise": {
|
| 11 |
+
"total": 20,
|
| 12 |
+
"correct": 10,
|
| 13 |
+
"accuracy": 0.5
|
| 14 |
+
},
|
| 15 |
+
"semantic_overlap": {
|
| 16 |
+
"total": 20,
|
| 17 |
+
"correct": 16,
|
| 18 |
+
"accuracy": 0.8
|
| 19 |
+
},
|
| 20 |
+
"edge_cases": {
|
| 21 |
+
"total": 20,
|
| 22 |
+
"correct": 11,
|
| 23 |
+
"accuracy": 0.55
|
| 24 |
+
}
|
| 25 |
+
},
|
| 26 |
+
"overall_accuracy": 0.6875,
|
| 27 |
+
"total_samples": 80,
|
| 28 |
+
"correct_samples": 55,
|
| 29 |
+
"samples": [
|
| 30 |
+
{
|
| 31 |
+
"text": "Ömer, nasıl yardımcı olabilirim?",
|
| 32 |
+
"expected_label": "agent_response",
|
| 33 |
+
"difficulty": "baseline",
|
| 34 |
+
"predicted_label": "agent_response",
|
| 35 |
+
"confidence": 0.8812354207038879,
|
| 36 |
+
"is_correct": true
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"text": "Merhaba, hangi konuda yardım edebilirim?",
|
| 40 |
+
"expected_label": "agent_response",
|
| 41 |
+
"difficulty": "baseline",
|
| 42 |
+
"predicted_label": "agent_response",
|
| 43 |
+
"confidence": 0.9911393523216248,
|
| 44 |
+
"is_correct": true
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"text": "Tabii ki, size bununla ilgili bilgi verebilirim.",
|
| 48 |
+
"expected_label": "agent_response",
|
| 49 |
+
"difficulty": "baseline",
|
| 50 |
+
"predicted_label": "agent_response",
|
| 51 |
+
"confidence": 0.5156869292259216,
|
| 52 |
+
"is_correct": true
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"text": "Elbette, bu konuda size destek olacağım.",
|
| 56 |
+
"expected_label": "agent_response",
|
| 57 |
+
"difficulty": "baseline",
|
| 58 |
+
"predicted_label": "backchannel",
|
| 59 |
+
"confidence": 0.5563545823097229,
|
| 60 |
+
"is_correct": false
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"text": "Anladım, hemen kontrol ediyorum.",
|
| 64 |
+
"expected_label": "agent_response",
|
| 65 |
+
"difficulty": "baseline",
|
| 66 |
+
"predicted_label": "backchannel",
|
| 67 |
+
"confidence": 0.5459677577018738,
|
| 68 |
+
"is_correct": false
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"text": "Lütfen bekleyin, birazdan yanıt vereceğim.",
|
| 72 |
+
"expected_label": "agent_response",
|
| 73 |
+
"difficulty": "baseline",
|
| 74 |
+
"predicted_label": "agent_response",
|
| 75 |
+
"confidence": 0.8637070655822754,
|
| 76 |
+
"is_correct": true
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"text": "Bu konuda yardımcı olmaktan memnuniyet duyarım.",
|
| 80 |
+
"expected_label": "agent_response",
|
| 81 |
+
"difficulty": "baseline",
|
| 82 |
+
"predicted_label": "agent_response",
|
| 83 |
+
"confidence": 0.6278860569000244,
|
| 84 |
+
"is_correct": true
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"text": "Hemen sizin için araştırıyorum.",
|
| 88 |
+
"expected_label": "agent_response",
|
| 89 |
+
"difficulty": "baseline",
|
| 90 |
+
"predicted_label": "agent_response",
|
| 91 |
+
"confidence": 0.7357267737388611,
|
| 92 |
+
"is_correct": true
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"text": "Endişelenmeyin, bu konuyu halledeceğiz.",
|
| 96 |
+
"expected_label": "agent_response",
|
| 97 |
+
"difficulty": "baseline",
|
| 98 |
+
"predicted_label": "agent_response",
|
| 99 |
+
"confidence": 0.6491527557373047,
|
| 100 |
+
"is_correct": true
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"text": "Herhangi başka bir sorunuz varsa, sormaktan çekinmeyin.",
|
| 104 |
+
"expected_label": "agent_response",
|
| 105 |
+
"difficulty": "baseline",
|
| 106 |
+
"predicted_label": "agent_response",
|
| 107 |
+
"confidence": 0.9041098952293396,
|
| 108 |
+
"is_correct": true
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"text": "totes agree lol",
|
| 112 |
+
"expected_label": "agent_response",
|
| 113 |
+
"difficulty": "length_noise",
|
| 114 |
+
"predicted_label": "backchannel",
|
| 115 |
+
"confidence": 0.9879427552223206,
|
| 116 |
+
"is_correct": false
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"text": "yup yup yup yup yup",
|
| 120 |
+
"expected_label": "agent_response",
|
| 121 |
+
"difficulty": "length_noise",
|
| 122 |
+
"predicted_label": "backchannel",
|
| 123 |
+
"confidence": 0.988431453704834,
|
| 124 |
+
"is_correct": false
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"text": "OMG cant believe u did that, like seriously, i mean come on, its just too much, you know what i mean? cuz if you dont then idk what to say, like seriously",
|
| 128 |
+
"expected_label": "agent_response",
|
| 129 |
+
"difficulty": "length_noise",
|
| 130 |
+
"predicted_label": "agent_response",
|
| 131 |
+
"confidence": 0.909318745136261,
|
| 132 |
+
"is_correct": true
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"text": "nah bro",
|
| 136 |
+
"expected_label": "agent_response",
|
| 137 |
+
"difficulty": "length_noise",
|
| 138 |
+
"predicted_label": "backchannel",
|
| 139 |
+
"confidence": 0.9873980283737183,
|
| 140 |
+
"is_correct": false
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"text": "yasss that's wassup",
|
| 144 |
+
"expected_label": "agent_response",
|
| 145 |
+
"difficulty": "length_noise",
|
| 146 |
+
"predicted_label": "backchannel",
|
| 147 |
+
"confidence": 0.974721372127533,
|
| 148 |
+
"is_correct": false
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"text": "okay okay okay i get it already no need to repeat urself over and over again like i'm not deaf or whatever",
|
| 152 |
+
"expected_label": "agent_response",
|
| 153 |
+
"difficulty": "length_noise",
|
| 154 |
+
"predicted_label": "agent_response",
|
| 155 |
+
"confidence": 0.9450967907905579,
|
| 156 |
+
"is_correct": true
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"text": "omg thts crazee",
|
| 160 |
+
"expected_label": "agent_response",
|
| 161 |
+
"difficulty": "length_noise",
|
| 162 |
+
"predicted_label": "backchannel",
|
| 163 |
+
"confidence": 0.9885514974594116,
|
| 164 |
+
"is_correct": false
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"text": "u r kidding right?",
|
| 168 |
+
"expected_label": "agent_response",
|
| 169 |
+
"difficulty": "length_noise",
|
| 170 |
+
"predicted_label": "backchannel",
|
| 171 |
+
"confidence": 0.9817968606948853,
|
| 172 |
+
"is_correct": false
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"text": "wow just wow, i mean, wow! i never thought that this would happen, like ever, not in a million years, and yet here we are, unbelievable, just totally unbelievable, you feel me?",
|
| 176 |
+
"expected_label": "agent_response",
|
| 177 |
+
"difficulty": "length_noise",
|
| 178 |
+
"predicted_label": "agent_response",
|
| 179 |
+
"confidence": 0.8823995590209961,
|
| 180 |
+
"is_correct": true
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"text": "hah lol whatevs",
|
| 184 |
+
"expected_label": "agent_response",
|
| 185 |
+
"difficulty": "length_noise",
|
| 186 |
+
"predicted_label": "backchannel",
|
| 187 |
+
"confidence": 0.9895368814468384,
|
| 188 |
+
"is_correct": false
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"text": "Ah, anlıyorum. Devam edebilir misiniz?",
|
| 192 |
+
"expected_label": "agent_response",
|
| 193 |
+
"difficulty": "semantic_overlap",
|
| 194 |
+
"predicted_label": "agent_response",
|
| 195 |
+
"confidence": 0.8250168561935425,
|
| 196 |
+
"is_correct": true
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"text": "Hmm, bunu biraz daha açabilir misiniz?",
|
| 200 |
+
"expected_label": "agent_response",
|
| 201 |
+
"difficulty": "semantic_overlap",
|
| 202 |
+
"predicted_label": "agent_response",
|
| 203 |
+
"confidence": 0.745111882686615,
|
| 204 |
+
"is_correct": true
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"text": "Evet, bu gerçekten ilginç. Daha fazla bilgi verebilir misiniz?",
|
| 208 |
+
"expected_label": "agent_response",
|
| 209 |
+
"difficulty": "semantic_overlap",
|
| 210 |
+
"predicted_label": "agent_response",
|
| 211 |
+
"confidence": 0.9849535226821899,
|
| 212 |
+
"is_correct": true
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"text": "Bu konuda düşündüğünüz başka bir şey var mı?",
|
| 216 |
+
"expected_label": "agent_response",
|
| 217 |
+
"difficulty": "semantic_overlap",
|
| 218 |
+
"predicted_label": "agent_response",
|
| 219 |
+
"confidence": 0.9519035220146179,
|
| 220 |
+
"is_correct": true
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"text": "Hımm, pekala. Başka bir açıdan bakacak olursak?",
|
| 224 |
+
"expected_label": "agent_response",
|
| 225 |
+
"difficulty": "semantic_overlap",
|
| 226 |
+
"predicted_label": "backchannel",
|
| 227 |
+
"confidence": 0.903683066368103,
|
| 228 |
+
"is_correct": false
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"text": "Evet, kesinlikle. Peki başka hangi yönlerini ele alabiliriz?",
|
| 232 |
+
"expected_label": "agent_response",
|
| 233 |
+
"difficulty": "semantic_overlap",
|
| 234 |
+
"predicted_label": "agent_response",
|
| 235 |
+
"confidence": 0.9927364587783813,
|
| 236 |
+
"is_correct": true
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"text": "Tamam, peki buna ek olarak ne söyleyebilirsiniz?",
|
| 240 |
+
"expected_label": "agent_response",
|
| 241 |
+
"difficulty": "semantic_overlap",
|
| 242 |
+
"predicted_label": "agent_response",
|
| 243 |
+
"confidence": 0.9534065127372742,
|
| 244 |
+
"is_correct": true
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"text": "Anladım, devam etmek ister misiniz?",
|
| 248 |
+
"expected_label": "agent_response",
|
| 249 |
+
"difficulty": "semantic_overlap",
|
| 250 |
+
"predicted_label": "agent_response",
|
| 251 |
+
"confidence": 0.974102795124054,
|
| 252 |
+
"is_correct": true
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"text": "Evet, peki başka bir detaya dikkat çekmek ister misiniz?",
|
| 256 |
+
"expected_label": "agent_response",
|
| 257 |
+
"difficulty": "semantic_overlap",
|
| 258 |
+
"predicted_label": "agent_response",
|
| 259 |
+
"confidence": 0.9879535436630249,
|
| 260 |
+
"is_correct": true
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"text": "Hmm, çok iyi bir nokta. Bunu biraz daha açar mısınız?",
|
| 264 |
+
"expected_label": "agent_response",
|
| 265 |
+
"difficulty": "semantic_overlap",
|
| 266 |
+
"predicted_label": "agent_response",
|
| 267 |
+
"confidence": 0.9757851362228394,
|
| 268 |
+
"is_correct": true
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"text": "Oh great, another software update that will surely make everything run faster, just like last time.",
|
| 272 |
+
"expected_label": "agent_response",
|
| 273 |
+
"difficulty": "edge_cases",
|
| 274 |
+
"predicted_label": "agent_response",
|
| 275 |
+
"confidence": 0.895721971988678,
|
| 276 |
+
"is_correct": true
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"text": "I'm sure the server downtime at exactly 5 PM on a Friday was purely coincidental, and not at all inconvenient.",
|
| 280 |
+
"expected_label": "agent_response",
|
| 281 |
+
"difficulty": "edge_cases",
|
| 282 |
+
"predicted_label": "agent_response",
|
| 283 |
+
"confidence": 0.849263072013855,
|
| 284 |
+
"is_correct": true
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"text": "Yeah, because deleting the database with a single command is exactly what everyone wants, right?",
|
| 288 |
+
"expected_label": "agent_response",
|
| 289 |
+
"difficulty": "edge_cases",
|
| 290 |
+
"predicted_label": "agent_response",
|
| 291 |
+
"confidence": 0.7744247317314148,
|
| 292 |
+
"is_correct": true
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"text": "I just love it when my AI assistant corrects me even when I'm right, it's like having a personal grammar teacher.",
|
| 296 |
+
"expected_label": "agent_response",
|
| 297 |
+
"difficulty": "edge_cases",
|
| 298 |
+
"predicted_label": "agent_response",
|
| 299 |
+
"confidence": 0.5396984815597534,
|
| 300 |
+
"is_correct": true
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"text": "No, I absolutely don't need any more disk space. Who needs to store files anyway?",
|
| 304 |
+
"expected_label": "agent_response",
|
| 305 |
+
"difficulty": "edge_cases",
|
| 306 |
+
"predicted_label": "agent_response",
|
| 307 |
+
"confidence": 0.9811112284660339,
|
| 308 |
+
"is_correct": true
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"text": "Sure, let's implement the new feature without any testing. What could possibly go wrong?",
|
| 312 |
+
"expected_label": "agent_response",
|
| 313 |
+
"difficulty": "edge_cases",
|
| 314 |
+
"predicted_label": "agent_response",
|
| 315 |
+
"confidence": 0.9612233638763428,
|
| 316 |
+
"is_correct": true
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"text": "Oh, another meeting about meetings? This is exactly why I got into tech.",
|
| 320 |
+
"expected_label": "agent_response",
|
| 321 |
+
"difficulty": "edge_cases",
|
| 322 |
+
"predicted_label": "agent_response",
|
| 323 |
+
"confidence": 0.9544288516044617,
|
| 324 |
+
"is_correct": true
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"text": "I'm really looking forward to debugging this code at 2 AM again. It's the highlight of my week.",
|
| 328 |
+
"expected_label": "agent_response",
|
| 329 |
+
"difficulty": "edge_cases",
|
| 330 |
+
"predicted_label": "agent_response",
|
| 331 |
+
"confidence": 0.8809834122657776,
|
| 332 |
+
"is_correct": true
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"text": "The best part of working with AI is when it confidently gives you the wrong answer.",
|
| 336 |
+
"expected_label": "agent_response",
|
| 337 |
+
"difficulty": "edge_cases",
|
| 338 |
+
"predicted_label": "agent_response",
|
| 339 |
+
"confidence": 0.8558328151702881,
|
| 340 |
+
"is_correct": true
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"text": "Of course, let’s deploy the untested code on a Friday evening, I have nothing better to do.",
|
| 344 |
+
"expected_label": "agent_response",
|
| 345 |
+
"difficulty": "edge_cases",
|
| 346 |
+
"predicted_label": "agent_response",
|
| 347 |
+
"confidence": 0.7736720442771912,
|
| 348 |
+
"is_correct": true
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"text": "Evet, seni anlıyorum.",
|
| 352 |
+
"expected_label": "backchannel",
|
| 353 |
+
"difficulty": "baseline",
|
| 354 |
+
"predicted_label": "backchannel",
|
| 355 |
+
"confidence": 0.8567759990692139,
|
| 356 |
+
"is_correct": true
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"text": "Hmm, ilginç.",
|
| 360 |
+
"expected_label": "backchannel",
|
| 361 |
+
"difficulty": "baseline",
|
| 362 |
+
"predicted_label": "backchannel",
|
| 363 |
+
"confidence": 0.985055685043335,
|
| 364 |
+
"is_correct": true
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"text": "Evet, devam et.",
|
| 368 |
+
"expected_label": "backchannel",
|
| 369 |
+
"difficulty": "baseline",
|
| 370 |
+
"predicted_label": "backchannel",
|
| 371 |
+
"confidence": 0.8956389427185059,
|
| 372 |
+
"is_correct": true
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"text": "Gerçekten mi?",
|
| 376 |
+
"expected_label": "backchannel",
|
| 377 |
+
"difficulty": "baseline",
|
| 378 |
+
"predicted_label": "backchannel",
|
| 379 |
+
"confidence": 0.9868144989013672,
|
| 380 |
+
"is_correct": true
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"text": "Tamam, bu mantıklı.",
|
| 384 |
+
"expected_label": "backchannel",
|
| 385 |
+
"difficulty": "baseline",
|
| 386 |
+
"predicted_label": "backchannel",
|
| 387 |
+
"confidence": 0.7614496946334839,
|
| 388 |
+
"is_correct": true
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"text": "Anladım.",
|
| 392 |
+
"expected_label": "backchannel",
|
| 393 |
+
"difficulty": "baseline",
|
| 394 |
+
"predicted_label": "backchannel",
|
| 395 |
+
"confidence": 0.9884626269340515,
|
| 396 |
+
"is_correct": true
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"text": "Evet, bu doğru.",
|
| 400 |
+
"expected_label": "backchannel",
|
| 401 |
+
"difficulty": "baseline",
|
| 402 |
+
"predicted_label": "backchannel",
|
| 403 |
+
"confidence": 0.8082573413848877,
|
| 404 |
+
"is_correct": true
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"text": "Ah, şimdi anlıyorum.",
|
| 408 |
+
"expected_label": "backchannel",
|
| 409 |
+
"difficulty": "baseline",
|
| 410 |
+
"predicted_label": "backchannel",
|
| 411 |
+
"confidence": 0.9578026533126831,
|
| 412 |
+
"is_correct": true
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"text": "Bu ilginç bir nokta.",
|
| 416 |
+
"expected_label": "backchannel",
|
| 417 |
+
"difficulty": "baseline",
|
| 418 |
+
"predicted_label": "backchannel",
|
| 419 |
+
"confidence": 0.6748051643371582,
|
| 420 |
+
"is_correct": true
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"text": "Evet, buna katılıyorum.",
|
| 424 |
+
"expected_label": "backchannel",
|
| 425 |
+
"difficulty": "baseline",
|
| 426 |
+
"predicted_label": "backchannel",
|
| 427 |
+
"confidence": 0.8088875412940979,
|
| 428 |
+
"is_correct": true
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"text": "yaaaa broooo",
|
| 432 |
+
"expected_label": "backchannel",
|
| 433 |
+
"difficulty": "length_noise",
|
| 434 |
+
"predicted_label": "backchannel",
|
| 435 |
+
"confidence": 0.9909811615943909,
|
| 436 |
+
"is_correct": true
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"text": "huh? r u srz??",
|
| 440 |
+
"expected_label": "backchannel",
|
| 441 |
+
"difficulty": "length_noise",
|
| 442 |
+
"predicted_label": "backchannel",
|
| 443 |
+
"confidence": 0.9855925440788269,
|
| 444 |
+
"is_correct": true
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"text": "OMG this is like the most amazing thing ever I mean I can't even begin to explain how incredible this whole situation is because it's just that awesome you know what I mean like seriously wow just wow ok???",
|
| 448 |
+
"expected_label": "backchannel",
|
| 449 |
+
"difficulty": "length_noise",
|
| 450 |
+
"predicted_label": "agent_response",
|
| 451 |
+
"confidence": 0.7402034997940063,
|
| 452 |
+
"is_correct": false
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"text": "idk wat u mean",
|
| 456 |
+
"expected_label": "backchannel",
|
| 457 |
+
"difficulty": "length_noise",
|
| 458 |
+
"predicted_label": "backchannel",
|
| 459 |
+
"confidence": 0.9897193908691406,
|
| 460 |
+
"is_correct": true
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"text": "sure sure sure sure sure",
|
| 464 |
+
"expected_label": "backchannel",
|
| 465 |
+
"difficulty": "length_noise",
|
| 466 |
+
"predicted_label": "backchannel",
|
| 467 |
+
"confidence": 0.9763302206993103,
|
| 468 |
+
"is_correct": true
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"text": "omg totally 100% agree with you on that one no doubt about it in fact I was just thinking the same thing the other day and it's crazy how we're like on the same wavelength all the time isn't it?",
|
| 472 |
+
"expected_label": "backchannel",
|
| 473 |
+
"difficulty": "length_noise",
|
| 474 |
+
"predicted_label": "agent_response",
|
| 475 |
+
"confidence": 0.9482101798057556,
|
| 476 |
+
"is_correct": false
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"text": "no wayyyy",
|
| 480 |
+
"expected_label": "backchannel",
|
| 481 |
+
"difficulty": "length_noise",
|
| 482 |
+
"predicted_label": "backchannel",
|
| 483 |
+
"confidence": 0.991447925567627,
|
| 484 |
+
"is_correct": true
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"text": "heyyy, u ther?",
|
| 488 |
+
"expected_label": "backchannel",
|
| 489 |
+
"difficulty": "length_noise",
|
| 490 |
+
"predicted_label": "backchannel",
|
| 491 |
+
"confidence": 0.990699827671051,
|
| 492 |
+
"is_correct": true
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"text": "wow cant believe it happened like that i mean who would have thought that everything would turn out this way after all the planning we did it just goes to show that sometimes things have a way of working out on their own despite all the odds and challenges we faced right from the start",
|
| 496 |
+
"expected_label": "backchannel",
|
| 497 |
+
"difficulty": "length_noise",
|
| 498 |
+
"predicted_label": "agent_response",
|
| 499 |
+
"confidence": 0.971515953540802,
|
| 500 |
+
"is_correct": false
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"text": "kk thx bye",
|
| 504 |
+
"expected_label": "backchannel",
|
| 505 |
+
"difficulty": "length_noise",
|
| 506 |
+
"predicted_label": "backchannel",
|
| 507 |
+
"confidence": 0.99072265625,
|
| 508 |
+
"is_correct": true
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"text": "Hmm, ilginç bir nokta.",
|
| 512 |
+
"expected_label": "backchannel",
|
| 513 |
+
"difficulty": "semantic_overlap",
|
| 514 |
+
"predicted_label": "backchannel",
|
| 515 |
+
"confidence": 0.9318225979804993,
|
| 516 |
+
"is_correct": true
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"text": "Anladım, peki ya sonra?",
|
| 520 |
+
"expected_label": "backchannel",
|
| 521 |
+
"difficulty": "semantic_overlap",
|
| 522 |
+
"predicted_label": "backchannel",
|
| 523 |
+
"confidence": 0.9160572290420532,
|
| 524 |
+
"is_correct": true
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"text": "Hmm, o konuda biraz daha bilgi verir misin?",
|
| 528 |
+
"expected_label": "backchannel",
|
| 529 |
+
"difficulty": "semantic_overlap",
|
| 530 |
+
"predicted_label": "agent_response",
|
| 531 |
+
"confidence": 0.7073332667350769,
|
| 532 |
+
"is_correct": false
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"text": "Gerçekten mi? Daha fazla duymak isterim.",
|
| 536 |
+
"expected_label": "backchannel",
|
| 537 |
+
"difficulty": "semantic_overlap",
|
| 538 |
+
"predicted_label": "backchannel",
|
| 539 |
+
"confidence": 0.7160800099372864,
|
| 540 |
+
"is_correct": true
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"text": "Bu mantıklı, başka neler oldu?",
|
| 544 |
+
"expected_label": "backchannel",
|
| 545 |
+
"difficulty": "semantic_overlap",
|
| 546 |
+
"predicted_label": "agent_response",
|
| 547 |
+
"confidence": 0.812181293964386,
|
| 548 |
+
"is_correct": false
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"text": "Hmm, bunu daha önce duymamıştım.",
|
| 552 |
+
"expected_label": "backchannel",
|
| 553 |
+
"difficulty": "semantic_overlap",
|
| 554 |
+
"predicted_label": "backchannel",
|
| 555 |
+
"confidence": 0.8978190422058105,
|
| 556 |
+
"is_correct": true
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"text": "Bir dakika, bunu doğru mu anlıyorum?",
|
| 560 |
+
"expected_label": "backchannel",
|
| 561 |
+
"difficulty": "semantic_overlap",
|
| 562 |
+
"predicted_label": "agent_response",
|
| 563 |
+
"confidence": 0.7696111798286438,
|
| 564 |
+
"is_correct": false
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"text": "Peki, sonra ne yaptılar?",
|
| 568 |
+
"expected_label": "backchannel",
|
| 569 |
+
"difficulty": "semantic_overlap",
|
| 570 |
+
"predicted_label": "backchannel",
|
| 571 |
+
"confidence": 0.6477120518684387,
|
| 572 |
+
"is_correct": true
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"text": "Gerçekten mi? Bu beni düşündürdü.",
|
| 576 |
+
"expected_label": "backchannel",
|
| 577 |
+
"difficulty": "semantic_overlap",
|
| 578 |
+
"predicted_label": "backchannel",
|
| 579 |
+
"confidence": 0.9161955714225769,
|
| 580 |
+
"is_correct": true
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"text": "İlginç, devam et lütfen.",
|
| 584 |
+
"expected_label": "backchannel",
|
| 585 |
+
"difficulty": "semantic_overlap",
|
| 586 |
+
"predicted_label": "backchannel",
|
| 587 |
+
"confidence": 0.7439655661582947,
|
| 588 |
+
"is_correct": true
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"text": "Evet evet, tabii ki de tebrik ederim, dünya harikası bir iş çıkardın (!)",
|
| 592 |
+
"expected_label": "backchannel",
|
| 593 |
+
"difficulty": "edge_cases",
|
| 594 |
+
"predicted_label": "agent_response",
|
| 595 |
+
"confidence": 0.877510666847229,
|
| 596 |
+
"is_correct": false
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"text": "Çok güzel, bu kadar net bir çözüm bulduğunu(!) hiç düşünmemiştim doğrusu.",
|
| 600 |
+
"expected_label": "backchannel",
|
| 601 |
+
"difficulty": "edge_cases",
|
| 602 |
+
"predicted_label": "agent_response",
|
| 603 |
+
"confidence": 0.9826798439025879,
|
| 604 |
+
"is_correct": false
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"text": "Ah, tabii ki! Çünkü herkes daima müşteri hizmetlerinin ne kadar hızlı olduğunu söyler (!)",
|
| 608 |
+
"expected_label": "backchannel",
|
| 609 |
+
"difficulty": "edge_cases",
|
| 610 |
+
"predicted_label": "agent_response",
|
| 611 |
+
"confidence": 0.5608082413673401,
|
| 612 |
+
"is_correct": false
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"text": "Eğer bu kadar 'yaratıcı' bir fikir daha duyar mıyım diye düşünüyordum, teşekkürler!",
|
| 616 |
+
"expected_label": "backchannel",
|
| 617 |
+
"difficulty": "edge_cases",
|
| 618 |
+
"predicted_label": "agent_response",
|
| 619 |
+
"confidence": 0.9653686881065369,
|
| 620 |
+
"is_correct": false
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"text": "Bir işin en iyi nasıl yapılmaması gerektiğini görmek için harika (!) bir örnekti.",
|
| 624 |
+
"expected_label": "backchannel",
|
| 625 |
+
"difficulty": "edge_cases",
|
| 626 |
+
"predicted_label": "agent_response",
|
| 627 |
+
"confidence": 0.9630967378616333,
|
| 628 |
+
"is_correct": false
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"text": "Evet, kesinlikle bugünkü toplantıda hiçbir şey anlaşılmadı diyemem.",
|
| 632 |
+
"expected_label": "backchannel",
|
| 633 |
+
"difficulty": "edge_cases",
|
| 634 |
+
"predicted_label": "agent_response",
|
| 635 |
+
"confidence": 0.8947334289550781,
|
| 636 |
+
"is_correct": false
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"text": "Harika, seninki gibi bir çözüm sayesinde sorunlarımız iki katına çıkacak (!)",
|
| 640 |
+
"expected_label": "backchannel",
|
| 641 |
+
"difficulty": "edge_cases",
|
| 642 |
+
"predicted_label": "agent_response",
|
| 643 |
+
"confidence": 0.8286226987838745,
|
| 644 |
+
"is_correct": false
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"text": "Tabii ki de, Türk çayı yurt dışında sudan bile ucuzdur (!).",
|
| 648 |
+
"expected_label": "backchannel",
|
| 649 |
+
"difficulty": "edge_cases",
|
| 650 |
+
"predicted_label": "backchannel",
|
| 651 |
+
"confidence": 0.8883209228515625,
|
| 652 |
+
"is_correct": true
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"text": "Bu kadar ‘detaylı’ bir analiz için üç cümle yeterli oldu, harikasın!",
|
| 656 |
+
"expected_label": "backchannel",
|
| 657 |
+
"difficulty": "edge_cases",
|
| 658 |
+
"predicted_label": "agent_response",
|
| 659 |
+
"confidence": 0.610821545124054,
|
| 660 |
+
"is_correct": false
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"text": "Elbette, herkesin sabırsızlıkla beklediği o 'harika' PowerPoint sunumunu bir daha görelim.",
|
| 664 |
+
"expected_label": "backchannel",
|
| 665 |
+
"difficulty": "edge_cases",
|
| 666 |
+
"predicted_label": "agent_response",
|
| 667 |
+
"confidence": 0.9590893387794495,
|
| 668 |
+
"is_correct": false
|
| 669 |
+
}
|
| 670 |
+
],
|
| 671 |
+
"misclassifications": [
|
| 672 |
+
{
|
| 673 |
+
"text": "Elbette, bu konuda size destek olacağım.",
|
| 674 |
+
"expected_label": "agent_response",
|
| 675 |
+
"difficulty": "baseline",
|
| 676 |
+
"predicted_label": "backchannel",
|
| 677 |
+
"confidence": 0.5563545823097229,
|
| 678 |
+
"is_correct": false
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"text": "Anladım, hemen kontrol ediyorum.",
|
| 682 |
+
"expected_label": "agent_response",
|
| 683 |
+
"difficulty": "baseline",
|
| 684 |
+
"predicted_label": "backchannel",
|
| 685 |
+
"confidence": 0.5459677577018738,
|
| 686 |
+
"is_correct": false
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"text": "totes agree lol",
|
| 690 |
+
"expected_label": "agent_response",
|
| 691 |
+
"difficulty": "length_noise",
|
| 692 |
+
"predicted_label": "backchannel",
|
| 693 |
+
"confidence": 0.9879427552223206,
|
| 694 |
+
"is_correct": false
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"text": "yup yup yup yup yup",
|
| 698 |
+
"expected_label": "agent_response",
|
| 699 |
+
"difficulty": "length_noise",
|
| 700 |
+
"predicted_label": "backchannel",
|
| 701 |
+
"confidence": 0.988431453704834,
|
| 702 |
+
"is_correct": false
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"text": "nah bro",
|
| 706 |
+
"expected_label": "agent_response",
|
| 707 |
+
"difficulty": "length_noise",
|
| 708 |
+
"predicted_label": "backchannel",
|
| 709 |
+
"confidence": 0.9873980283737183,
|
| 710 |
+
"is_correct": false
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"text": "yasss that's wassup",
|
| 714 |
+
"expected_label": "agent_response",
|
| 715 |
+
"difficulty": "length_noise",
|
| 716 |
+
"predicted_label": "backchannel",
|
| 717 |
+
"confidence": 0.974721372127533,
|
| 718 |
+
"is_correct": false
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"text": "omg thts crazee",
|
| 722 |
+
"expected_label": "agent_response",
|
| 723 |
+
"difficulty": "length_noise",
|
| 724 |
+
"predicted_label": "backchannel",
|
| 725 |
+
"confidence": 0.9885514974594116,
|
| 726 |
+
"is_correct": false
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"text": "u r kidding right?",
|
| 730 |
+
"expected_label": "agent_response",
|
| 731 |
+
"difficulty": "length_noise",
|
| 732 |
+
"predicted_label": "backchannel",
|
| 733 |
+
"confidence": 0.9817968606948853,
|
| 734 |
+
"is_correct": false
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"text": "hah lol whatevs",
|
| 738 |
+
"expected_label": "agent_response",
|
| 739 |
+
"difficulty": "length_noise",
|
| 740 |
+
"predicted_label": "backchannel",
|
| 741 |
+
"confidence": 0.9895368814468384,
|
| 742 |
+
"is_correct": false
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"text": "Hımm, pekala. Başka bir açıdan bakacak olursak?",
|
| 746 |
+
"expected_label": "agent_response",
|
| 747 |
+
"difficulty": "semantic_overlap",
|
| 748 |
+
"predicted_label": "backchannel",
|
| 749 |
+
"confidence": 0.903683066368103,
|
| 750 |
+
"is_correct": false
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"text": "OMG this is like the most amazing thing ever I mean I can't even begin to explain how incredible this whole situation is because it's just that awesome you know what I mean like seriously wow just wow ok???",
|
| 754 |
+
"expected_label": "backchannel",
|
| 755 |
+
"difficulty": "length_noise",
|
| 756 |
+
"predicted_label": "agent_response",
|
| 757 |
+
"confidence": 0.7402034997940063,
|
| 758 |
+
"is_correct": false
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"text": "omg totally 100% agree with you on that one no doubt about it in fact I was just thinking the same thing the other day and it's crazy how we're like on the same wavelength all the time isn't it?",
|
| 762 |
+
"expected_label": "backchannel",
|
| 763 |
+
"difficulty": "length_noise",
|
| 764 |
+
"predicted_label": "agent_response",
|
| 765 |
+
"confidence": 0.9482101798057556,
|
| 766 |
+
"is_correct": false
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"text": "wow cant believe it happened like that i mean who would have thought that everything would turn out this way after all the planning we did it just goes to show that sometimes things have a way of working out on their own despite all the odds and challenges we faced right from the start",
|
| 770 |
+
"expected_label": "backchannel",
|
| 771 |
+
"difficulty": "length_noise",
|
| 772 |
+
"predicted_label": "agent_response",
|
| 773 |
+
"confidence": 0.971515953540802,
|
| 774 |
+
"is_correct": false
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"text": "Hmm, o konuda biraz daha bilgi verir misin?",
|
| 778 |
+
"expected_label": "backchannel",
|
| 779 |
+
"difficulty": "semantic_overlap",
|
| 780 |
+
"predicted_label": "agent_response",
|
| 781 |
+
"confidence": 0.7073332667350769,
|
| 782 |
+
"is_correct": false
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"text": "Bu mantıklı, başka neler oldu?",
|
| 786 |
+
"expected_label": "backchannel",
|
| 787 |
+
"difficulty": "semantic_overlap",
|
| 788 |
+
"predicted_label": "agent_response",
|
| 789 |
+
"confidence": 0.812181293964386,
|
| 790 |
+
"is_correct": false
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"text": "Bir dakika, bunu doğru mu anlıyorum?",
|
| 794 |
+
"expected_label": "backchannel",
|
| 795 |
+
"difficulty": "semantic_overlap",
|
| 796 |
+
"predicted_label": "agent_response",
|
| 797 |
+
"confidence": 0.7696111798286438,
|
| 798 |
+
"is_correct": false
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"text": "Evet evet, tabii ki de tebrik ederim, dünya harikası bir iş çıkardın (!)",
|
| 802 |
+
"expected_label": "backchannel",
|
| 803 |
+
"difficulty": "edge_cases",
|
| 804 |
+
"predicted_label": "agent_response",
|
| 805 |
+
"confidence": 0.877510666847229,
|
| 806 |
+
"is_correct": false
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"text": "Çok güzel, bu kadar net bir çözüm bulduğunu(!) hiç düşünmemiştim doğrusu.",
|
| 810 |
+
"expected_label": "backchannel",
|
| 811 |
+
"difficulty": "edge_cases",
|
| 812 |
+
"predicted_label": "agent_response",
|
| 813 |
+
"confidence": 0.9826798439025879,
|
| 814 |
+
"is_correct": false
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"text": "Ah, tabii ki! Çünkü herkes daima müşteri hizmetlerinin ne kadar hızlı olduğunu söyler (!)",
|
| 818 |
+
"expected_label": "backchannel",
|
| 819 |
+
"difficulty": "edge_cases",
|
| 820 |
+
"predicted_label": "agent_response",
|
| 821 |
+
"confidence": 0.5608082413673401,
|
| 822 |
+
"is_correct": false
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"text": "Eğer bu kadar 'yaratıcı' bir fikir daha duyar mıyım diye düşünüyordum, teşekkürler!",
|
| 826 |
+
"expected_label": "backchannel",
|
| 827 |
+
"difficulty": "edge_cases",
|
| 828 |
+
"predicted_label": "agent_response",
|
| 829 |
+
"confidence": 0.9653686881065369,
|
| 830 |
+
"is_correct": false
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"text": "Bir işin en iyi nasıl yapılmaması gerektiğini görmek için harika (!) bir örnekti.",
|
| 834 |
+
"expected_label": "backchannel",
|
| 835 |
+
"difficulty": "edge_cases",
|
| 836 |
+
"predicted_label": "agent_response",
|
| 837 |
+
"confidence": 0.9630967378616333,
|
| 838 |
+
"is_correct": false
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"text": "Evet, kesinlikle bugünkü toplantıda hiçbir şey anlaşılmadı diyemem.",
|
| 842 |
+
"expected_label": "backchannel",
|
| 843 |
+
"difficulty": "edge_cases",
|
| 844 |
+
"predicted_label": "agent_response",
|
| 845 |
+
"confidence": 0.8947334289550781,
|
| 846 |
+
"is_correct": false
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"text": "Harika, seninki gibi bir çözüm sayesinde sorunlarımız iki katına çıkacak (!)",
|
| 850 |
+
"expected_label": "backchannel",
|
| 851 |
+
"difficulty": "edge_cases",
|
| 852 |
+
"predicted_label": "agent_response",
|
| 853 |
+
"confidence": 0.8286226987838745,
|
| 854 |
+
"is_correct": false
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"text": "Bu kadar ‘detaylı’ bir analiz için üç cümle yeterli oldu, harikasın!",
|
| 858 |
+
"expected_label": "backchannel",
|
| 859 |
+
"difficulty": "edge_cases",
|
| 860 |
+
"predicted_label": "agent_response",
|
| 861 |
+
"confidence": 0.610821545124054,
|
| 862 |
+
"is_correct": false
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"text": "Elbette, herkesin sabırsızlıkla beklediği o 'harika' PowerPoint sunumunu bir daha görelim.",
|
| 866 |
+
"expected_label": "backchannel",
|
| 867 |
+
"difficulty": "edge_cases",
|
| 868 |
+
"predicted_label": "agent_response",
|
| 869 |
+
"confidence": 0.9590893387794495,
|
| 870 |
+
"is_correct": false
|
| 871 |
+
}
|
| 872 |
+
]
|
| 873 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 768,
|
| 10 |
+
"id2label": {
|
| 11 |
+
"0": "agent_response",
|
| 12 |
+
"1": "backchannel"
|
| 13 |
+
},
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"label2id": {
|
| 17 |
+
"agent_response": 0,
|
| 18 |
+
"backchannel": 1
|
| 19 |
+
},
|
| 20 |
+
"layer_norm_eps": 1e-12,
|
| 21 |
+
"max_position_embeddings": 512,
|
| 22 |
+
"model_type": "bert",
|
| 23 |
+
"num_attention_heads": 12,
|
| 24 |
+
"num_hidden_layers": 12,
|
| 25 |
+
"pad_token_id": 0,
|
| 26 |
+
"position_embedding_type": "absolute",
|
| 27 |
+
"problem_type": "multi_label_classification",
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.52.4",
|
| 30 |
+
"type_vocab_size": 2,
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"vocab_size": 32000
|
| 33 |
+
}
|
evaluation_results.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"overall": {
|
| 3 |
+
"macro_f1": 0.9924276856095726,
|
| 4 |
+
"micro_f1": 0.9932420416147963,
|
| 5 |
+
"mcc": 0.9848560799888242,
|
| 6 |
+
"accuracy": 99.32420416147963
|
| 7 |
+
},
|
| 8 |
+
"per_class": {
|
| 9 |
+
"agent_response": {
|
| 10 |
+
"accuracy": 99.53108252947482,
|
| 11 |
+
"correct": 7429,
|
| 12 |
+
"total": 7464
|
| 13 |
+
},
|
| 14 |
+
"backchannel": {
|
| 15 |
+
"accuracy": 98.91591750396616,
|
| 16 |
+
"correct": 3741,
|
| 17 |
+
"total": 3782
|
| 18 |
+
}
|
| 19 |
+
},
|
| 20 |
+
"labels": [
|
| 21 |
+
"agent_response",
|
| 22 |
+
"backchannel"
|
| 23 |
+
],
|
| 24 |
+
"evaluated_at": "2025-12-14T21:35:53.969061"
|
| 25 |
+
}
|
label_config.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"labels": [
|
| 3 |
+
"agent_response",
|
| 4 |
+
"backchannel"
|
| 5 |
+
],
|
| 6 |
+
"id2label": {
|
| 7 |
+
"0": "agent_response",
|
| 8 |
+
"1": "backchannel"
|
| 9 |
+
},
|
| 10 |
+
"label2id": {
|
| 11 |
+
"agent_response": 0,
|
| 12 |
+
"backchannel": 1
|
| 13 |
+
},
|
| 14 |
+
"num_labels": 2,
|
| 15 |
+
"base_model": "dbmdz/bert-base-turkish-uncased",
|
| 16 |
+
"trained_at": "2025-12-14T21:35:28.772117"
|
| 17 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0045c21ba8bef6fde11ce20a30700a63b715c2d0c40cf82c1d7bcab17adab137
|
| 3 |
+
size 442499064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": true,
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "[MASK]",
|
| 50 |
+
"max_len": 512,
|
| 51 |
+
"model_max_length": 512,
|
| 52 |
+
"never_split": null,
|
| 53 |
+
"pad_token": "[PAD]",
|
| 54 |
+
"sep_token": "[SEP]",
|
| 55 |
+
"strip_accents": null,
|
| 56 |
+
"tokenize_chinese_chars": true,
|
| 57 |
+
"tokenizer_class": "BertTokenizer",
|
| 58 |
+
"unk_token": "[UNK]"
|
| 59 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1502a401bd9d1d7469710211efa36b287addea220a6762248357b0afb9e79f51
|
| 3 |
+
size 5841
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|