README.md

---
language: en
pipeline_tag: sentence-similarity
tags:
- patent-similarity
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
datasets:
- mpi-inno-comp/paecter_dataset
license: apache-2.0
---

# pat_specter

This is a [sentence-transformers](https://www.SBERT.net) model. This model is fine-tuned on patent texts, leveraging SPECTER 2.0 as a base, which is provided by Allen Institute for AI. It maps patent text to a 768 dimensional dense vector space and can be used for patent-specific downstream tasks.
However, it is noteworthy that [PaECTER](https://huggingface.co/mpi-inno-comp/paecter) outperforms this model in terms of performance.

## Usage (Sentence-Transformers)

Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:

```
pip install -U sentence-transformers
```

Then you can use the model like this:

```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]

model = SentenceTransformer('mpi-inno-comp/pat_specter')
embeddings = model.encode(sentences)
print(embeddings)
```



## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.

```python
from transformers import AutoTokenizer, AutoModel
import torch


def cls_pooling(model_output, attention_mask):
    return model_output[0][:,0]


# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']

# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('mpi-inno-comp/pat_specter')
model = AutoModel.from_pretrained('mpi-inno-comp/pat_specter')

# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt', max_length=512)

# Compute token embeddings
with torch.no_grad():
    model_output = model(**encoded_input)

# Perform pooling. In this case, cls pooling.
sentence_embeddings = cls_pooling(model_output, encoded_input['attention_mask'])

print("Sentence embeddings:")
print(sentence_embeddings)
```


## Training
The model was trained with the parameters:

**DataLoader**:

`torch.utils.data.dataloader.DataLoader` of length 159375 with parameters:
```
{'batch_size': 8, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
```

**Loss**:

`sentence_transformers.losses.CustomTripletLoss.CustomTripletLoss` with parameters:
  ```
  {'distance_metric': 'TripletDistanceMetric.EUCLIDEAN', 'triplet_margin': 1}
  ```

Parameters of the fit()-Method:
```
{
    "epochs": 1,
    "evaluation_steps": 2000,
    "evaluator": "sentence_transformers.evaluation.TripletEvaluator.TripletEvaluator",
    "max_grad_norm": 1,
    "optimizer_class": "<class 'transformers.optimization.AdamW'>",
    "optimizer_params": {
        "lr": 1e-05
    },
    "scheduler": "WarmupLinear",
    "steps_per_epoch": null,
    "warmup_steps": 10000,
    "weight_decay": 0.01
}
```


## Full Model Architecture
```
SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False})
)
```

## Citing & Authors
```
@misc{ghosh2024paecter,
      title={PaECTER: Patent-level Representation Learning using Citation-informed Transformers}, 
      author={Mainak Ghosh and Sebastian Erhardt and Michael E. Rose and Erik Buunk and Dietmar Harhoff},
      year={2024},
      eprint={2402.19411},
      archivePrefix={arXiv},
      primaryClass={cs.IR}
}
```