|
--- |
|
pipeline_tag: sentence-similarity |
|
tags: |
|
- sentence-transformers |
|
- feature-extraction |
|
- sentence-similarity |
|
- transformers |
|
language: |
|
- es |
|
datasets: |
|
- hackathon-pln-es/parallel-sentences |
|
widget: |
|
- text: "A ver si nos tenemos que poner todos en huelga hasta cobrar lo que queramos." |
|
- text: "La huelga es el método de lucha más eficaz para conseguir mejoras en el salario." |
|
- text: "Tendremos que optar por hacer una huelga para cobrar lo que queremos." |
|
- text: "Queda descartada la huelga aunque no cobremos lo que queramos." |
|
--- |
|
|
|
|
|
# paraphrase-spanish-distilroberta |
|
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search. |
|
|
|
We follow a **teacher-student** transfer learning approach to train an `bertin-roberta-base-spanish` model using parallel EN-ES sentence pairs. |
|
|
|
## 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 = ["Este es un ejemplo", "Cada oración es transformada"] |
|
|
|
model = SentenceTransformer('hackathon-pln-es/paraphrase-spanish-distilroberta') |
|
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 |
|
import torch.nn.functional as F |
|
|
|
#Mean Pooling - Take attention mask into account for correct averaging |
|
def mean_pooling(model_output, attention_mask): |
|
token_embeddings = model_output[0] #First element of model_output contains all token embeddings |
|
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float() |
|
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9) |
|
|
|
|
|
# Sentences we want sentence embeddings for |
|
sentences = ['Este es un ejemplo", "Cada oración es transformada'] |
|
|
|
# Load model from HuggingFace Hub |
|
tokenizer = AutoTokenizer.from_pretrained('hackathon-pln-es/paraphrase-spanish-distilroberta') |
|
model = AutoModel.from_pretrained('hackathon-pln-es/paraphrase-spanish-distilroberta') |
|
|
|
# Tokenize sentences |
|
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt') |
|
|
|
# Compute token embeddings |
|
with torch.no_grad(): |
|
model_output = model(**encoded_input) |
|
|
|
# Perform pooling |
|
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask']) |
|
|
|
# Normalize embeddings |
|
sentence_embeddings = F.normalize(sentence_embeddings, p=2, dim=1) |
|
|
|
print("Sentence embeddings:") |
|
print(sentence_embeddings) |
|
``` |
|
|
|
## Full Model Architecture |
|
``` |
|
SentenceTransformer( |
|
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel |
|
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False}) |
|
) |
|
``` |
|
|
|
## Evaluation Results |
|
|
|
Similarity Evaluation on STS-2017.es-en.txt and STS-2017.es-es.txt (translated manually for evaluation purposes) |
|
|
|
We measure the semantic textual similarity (STS) between sentence pairs in different languages: |
|
|
|
### ES-ES |
|
| cosine_pearson | cosine_spearman | manhattan_pearson | manhattan_spearman | euclidean_pearson | euclidean_spearman | dot_pearson | dot_spearman | |
|
| ----------- | ----------- | ----------- | ----------- | ----------- | ----------- | ----------- | ----------- | |
|
0.8495 | 0.8579 | 0.8675 | 0.8474 | 0.8676 | 0.8478 | 0.8277 | 0.8258 | |
|
|
|
### ES-EN |
|
| cosine_pearson | cosine_spearman | manhattan_pearson | manhattan_spearman | euclidean_pearson | euclidean_spearman | dot_pearson | dot_spearman | |
|
| ----------- | ----------- | ----------- | ----------- | ----------- | ----------- | ----------- | ----------- | |
|
0.8344 | 0.8448 | 0.8279 | 0.8168 | 0.8282 | 0.8159 | 0.8083 | 0.8145 | |
|
|
|
------ |
|
|
|
|
|
## Intended uses |
|
|
|
Our model is intented to be used as a sentence and short paragraph encoder. Given an input text, it ouptuts a vector which captures |
|
the semantic information. The sentence vector may be used for information retrieval, clustering or sentence similarity tasks. |
|
|
|
## Background |
|
|
|
This model is a bilingual Spanish-English model trained according to instructions in the paper [Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation](https://arxiv.org/pdf/2004.09813.pdf) and the [documentation](https://www.sbert.net/examples/training/multilingual/README.html) accompanying its companion python package. We have used the strongest available pretrained English Bi-Encoder ([paraphrase-mpnet-base-v2](https://www.sbert.net/docs/pretrained_models.html#sentence-embedding-models)) as a teacher model, and the pretrained Spanish [BERTIN](https://huggingface.co/bertin-project/bertin-roberta-base-spanish) as the student model. |
|
|
|
|
|
We developped this model during the |
|
[Hackathon 2022 NLP - Spanish](https://somosnlp.org/hackathon), |
|
organized by hackathon-pln-es Organization. |
|
|
|
### Training data |
|
|
|
We use the concatenation from multiple datasets with sentence pairs (EN-ES). |
|
We could check out the dataset that was used during training: [parallel-sentences](https://huggingface.co/datasets/hackathon-pln-es/parallel-sentences) |
|
|
|
| Dataset | |
|
|--------------------------------------------------------| |
|
| AllNLI - ES (SNLI + MultiNLI)| |
|
| EuroParl | |
|
| JW300 | |
|
| News Commentary | |
|
| Open Subtitles | |
|
| TED 2020 | |
|
| Tatoeba | |
|
| WikiMatrix | |
|
|
|
## Authors |
|
|
|
- [Anibal Pérez](https://huggingface.co/Anarpego), |
|
- [Emilio Tomás Ariza](https://huggingface.co/medardodt), |
|
- [Lautaro Gesuelli Pinto](https://huggingface.co/lautaro) |
|
- [Mauricio Mazuecos](https://huggingface.co/mmazuecos) |
