README.md

metadata

pipeline_tag: sentence-similarity
language: fr
license: mit
datasets:
  - unicamp-dl/mmarco
metrics:
  - recall
tags:
  - passage-retrieval
library_name: sentence-transformers
base_model: nreimers/mMiniLMv2-L12-H384-distilled-from-XLMR-Large
model-index:
  - name: biencoder-mMiniLMv2-L12-mmarcoFR
    results:
      - task:
          type: sentence-similarity
          name: Passage Retrieval
        dataset:
          type: unicamp-dl/mmarco
          name: mMARCO-fr
          config: french
          split: validation
        metrics:
          - type: recall_at_500
            name: Recall@500
            value: 84.42
          - type: recall_at_100
            name: Recall@100
            value: 71.52
          - type: recall_at_10
            name: Recall@10
            value: 45.4
          - type: map_at_10
            name: MAP@10
            value: 24.23
          - type: ndcg_at_10
            name: nDCG@10
            value: 29.41
          - type: mrr_at_10
            name: MRR@10
            value: 24.74

biencoder-mMiniLMv2-L12-mmarcoFR

This is a dense single-vector bi-encoder model. It maps sentences and paragraphs to a 384 dimensional dense vector space and should be used for semantic search. The model was trained on the French portion of the mMARCO retrieval dataset.

Usage

Here are some examples for using the model with Sentence-Transformers, FlagEmbedding, or Huggingface Transformers.

Using Sentence-Transformers

Start by installing the library: pip install -U sentence-transformers. Then, you can use the model like this:

from sentence_transformers import SentenceTransformer

queries = ["Ceci est un exemple de requête.", "Voici un second exemple."]
passages = ["Ceci est un exemple de passage.", "Et voilà un deuxième exemple."]

model = SentenceTransformer('antoinelouis/biencoder-mMiniLMv2-L12-mmarcoFR')
q_embeddings = model.encode(queries, normalize_embeddings=True)
p_embeddings = model.encode(passages, normalize_embeddings=True)

similarity = q_embeddings @ p_embeddings.T
print(similarity)

Using FlagEmbedding

Start by installing the library: pip install -U FlagEmbedding. Then, you can use the model like this:

from FlagEmbedding import FlagModel

queries = ["Ceci est un exemple de requête.", "Voici un second exemple."]
passages = ["Ceci est un exemple de passage.", "Et voilà un deuxième exemple."]

model = FlagModel('antoinelouis/biencoder-mMiniLMv2-L12-mmarcoFR')
q_embeddings = model.encode(queries, normalize_embeddings=True)
p_embeddings = model.encode(passages, normalize_embeddings=True)

similarity = q_embeddings @ p_embeddings.T
print(similarity)

Using Transformers

Start by installing the library: pip install -U transformers. Then, you can use the model like this:

from transformers import AutoTokenizer, AutoModel
from torch.nn.functional import normalize

def mean_pooling(model_output, attention_mask):
    """ Perform mean pooling on-top of the contextualized word embeddings, while ignoring mask tokens in the mean computation."""
    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)


queries = ["Ceci est un exemple de requête.", "Voici un second exemple."]
passages = ["Ceci est un exemple de passage.", "Et voilà un deuxième exemple."]

tokenizer = AutoTokenizer.from_pretrained('antoinelouis/biencoder-mMiniLMv2-L12-mmarcoFR')
model = AutoModel.from_pretrained('antoinelouis/biencoder-mMiniLMv2-L12-mmarcoFR')

q_input = tokenizer(queries, padding=True, truncation=True, return_tensors='pt')
p_input = tokenizer(passages, padding=True, truncation=True, return_tensors='pt')
with torch.no_grad():
    q_output = model(**encoded_queries)
    p_output = model(**encoded_passages)
q_embeddings = mean_pooling(q_output, q_input['attention_mask'])
q_embedddings = normalize(q_embeddings, p=2, dim=1)
p_embeddings = mean_pooling(p_output, p_input['attention_mask'])
p_embedddings = normalize(p_embeddings, p=2, dim=1)

similarity = q_embeddings @ p_embeddings.T
print(similarity)

---

Evaluation

We evaluate the model on the smaller development set of mMARCO-fr, which consists of 6,980 queries for a corpus of 8.8M candidate passages. Below, we compare the model performance with other biencoder models fine-tuned on the same dataset. We report the mean reciprocal rank (MRR), normalized discounted cumulative gainand (NDCG), mean average precision (MAP), and recall at various cut-offs (R@k).

	model	Vocab.	#Param.	Size	MRR@10	NDCG@10	MAP@10	R@10	R@100(↑)	R@500
1	biencoder-camembert-base-mmarcoFR	🇫🇷	110M	443MB	28.53	33.72	27.93	51.46	77.82	89.13
2	biencoder-mpnet-base-all-v2-mmarcoFR	🇬🇧	109M	438MB	28.04	33.28	27.50	51.07	77.68	88.67
3	biencoder-distilcamembert-mmarcoFR	🇫🇷	68M	272MB	26.80	31.87	26.23	49.20	76.44	87.87
4	biencoder-MiniLM-L6-all-v2-mmarcoFR	🇬🇧	23M	91MB	25.49	30.39	24.99	47.10	73.48	86.09
5	biencoder-mMiniLMv2-L12-mmarcoFR	🇫🇷,99+	117M	471MB	24.74	29.41	24.23	45.40	71.52	84.42
6	biencoder-camemberta-base-mmarcoFR	🇫🇷	112M	447MB	24.78	29.24	24.23	44.58	69.59	82.18
7	biencoder-electra-base-french-mmarcoFR	🇫🇷	110M	440MB	23.38	27.97	22.91	43.50	68.96	81.61
8	biencoder-mMiniLMv2-L6-mmarcoFR	🇫🇷,99+	107M	428MB	22.29	26.57	21.80	41.25	66.78	79.83

---

Training

Data

We use the French training samples from the mMARCO dataset, a multilingual machine-translated version of MS MARCO that contains 8.8M passages and 539K training queries. We do not employ the BM25 netaives provided by the official dataset but instead sample harder negatives mined from 12 distinct dense retrievers, using the msmarco-hard-negatives distillation dataset.

Implementation

The model is initialized from the nreimers/mMiniLMv2-L12-H384-distilled-from-XLMR-Large checkpoint and optimized via the cross-entropy loss (as in DPR) with a temperature of 0.05. It is fine-tuned on one 32GB NVIDIA V100 GPU for 20 epochs (i.e., 65.7k steps) using the AdamW optimizer with a batch size of 152, a peak learning rate of 2e-5 with warm up along the first 500 steps and linear scheduling. We set the maximum sequence lengths for both the questions and passages to 128 tokens. We use the cosine similarity to compute relevance scores.

---

Citation

@online{louis2023,
   author    = 'Antoine Louis',
   title     = 'biencoder-mMiniLMv2-L12-mmarcoFR: A Biencoder Model Trained on French mMARCO',
   publisher = 'Hugging Face',
   month     = 'may',
   year      = '2023',
   url       = 'https://huggingface.co/antoinelouis/biencoder-mMiniLMv2-L12-mmarcoFR',
}