File size: 2,412 Bytes
5f7f5f1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 | ---
license: mit
language: en
tags:
- rnn
- lstm
- chatbot
- dialogue-generation
- funny
pretty_name: "RNN AI-bot - The Apologetic Seat Obsessor"
---
# RNN AI-bot
This is a small, simple, and **grammatically flawless** but semantically clueless chatbot. It was trained on the DailyDialog dataset using a character-level RNN (LSTM) with a vocabulary of 10,002 tokens (including PAD and UNK).
## Model Details
- **Architecture**: LSTM (256 units) + Embedding (128 dims)
- **Input Length**: 50 tokens (context window)
- **Vocabulary Size**: 10,002
- **Training Data**: DailyDialog (13k dialogues, ~8 turns each)
- **Framework**: TensorFlow/Keras
## How to Use
```python
from tensorflow.keras.models import load_model
from tensorflow.keras.preprocessing.sequence import pad_sequences
model = load_model("best_model.h5")
# You'll need the word list and ID mappings.
# See the GitHub repo for full chat script.Performance & Quirks
The model generates grammatically correct English sentences but has no semantic understanding. It tends to:
Apologize excessively ("I am sorry.")
Obsess over the word "seat"
Insert "?" randomly
Get stuck in repetitive loops
Example Conversation
text
User: How are you?
Bot: I am a student in the mood for a while .
User: What are you studying?
Bot: I am applying for a vacation .
User: Did you get the vacation?
Bot: Yes , I am going to get a lot of the ? .
User: Where will you go?
Bot: I don't know what's a ? .
User: Seat?
Bot: Yes , I am going to get a lot of the ? .
User: ?
Bot: I don't know what's a seat .
Why Does It Behave Like This?
Small training: Only 10 epochs on CPU.
Limited context: 50-token window.
No pretrained embeddings: Learned everything from scratch.
Data bias: The word "seat" appears frequently in DailyDialog.
Full Source Code
All preprocessing, training, and chat scripts are available on GitHub:
👉 zyxdtt/Fun-Project/tree/main/RNN_AI-bot
There you'll find:
preprocessing.cpp – C++ data pipeline
RNN_train.py – Model training code
chat_test.py – Interactive chat script
Chat screenshots showing its hilarious responses
Fun Fact
This is the first AI project completed by a university freshman. It may be dumb, but it's 100% my own work — from data processing to deployment.
This bot proves that perfect grammar doesn't equal intelligence. It's a lesson in overfitting, data bias, and the importance of semantics. 😅 |