pipeline_tag: sentence-similarity
language:
- multilingual
- af
- am
- ar
- az
- be
- bg
- bn
- ca
- cs
- cy
- da
- de
- el
- en
- eo
- es
- et
- eu
- fa
- fi
- fr
- ga
- gl
- gu
- ha
- he
- hi
- hr
- hu
- hy
- id
- is
- it
- ja
- ka
- kk
- km
- kn
- ko
- ku
- ky
- la
- lo
- lt
- lv
- mk
- ml
- mn
- mr
- ms
- my
- ne
- nl
- 'no'
- or
- pa
- pl
- ps
- pt
- ro
- ru
- sa
- si
- sk
- sl
- so
- sq
- sr
- sv
- sw
- ta
- te
- th
- tl
- tr
- uk
- ur
- uz
- vi
- zh
license: apache-2.0
datasets:
- ms_marco
- sentence-transformers/msmarco-hard-negatives
metrics:
- recall
tags:
- feature-extraction
- sentence-similarity
library_name: sentence-transformers
DPR-XM
🛠️ Usage | 📊 Evaluation | 🤖 Training | 🔗 Citation | 🔑 License
This is a sentence-transformers model. It maps questions and paragraphs 768-dimensional dense vectors and can be used for semantic search. The model uses an XMOD backbone, which allows it to learn from monolingual fine-tuning in a high-resource language, like English, and perform zero-shot retrieval across multiple languages.
Usage
Here are some examples for using DPR-XM with Sentence-Transformers, FlagEmbedding, and 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."]
language_code = "fr_FR" #Find all codes here: https://huggingface.co/facebook/xmod-base#languages
model = SentenceTransformer('antoinelouis/dpr-xm')
model[0].auto_model.set_default_language(language_code) #Activate the language-specific adapters
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."]
language_code = "fr_FR" #Find all codes here: https://huggingface.co/facebook/xmod-base#languages
tokenizer = AutoTokenizer.from_pretrained('antoinelouis/dpr-xm')
model = AutoModel.from_pretrained('antoinelouis/dpr-xm')
model.set_default_language(language_code) #Activate the language-specific adapters
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)
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."]
language_code = "fr_FR" #Find all codes here: https://huggingface.co/facebook/xmod-base#languages
model = FlagModel('antoinelouis/dpr-xm')
model.model.set_default_language(language_code) #Activate the language-specific adapters
q_embeddings = model.encode(queries, normalize_embeddings=True)
p_embeddings = model.encode(passages, normalize_embeddings=True)
similarity = q_embeddings @ p_embeddings.T
print(similarity)
Evaluation
- MS MARCO: We evaluate our model on the small development set of MS MARCO, which consists of 6,980 queries for a corpus of 8.8M candidate passages. Below, we compared its performance with other retrieval models on the official metrics for the dataset, i.e., mean reciprocal rank at cut-off 10 (MRR@10).
| model | Type | #Samples | #Params | en | es | fr | it | pt | id | de | ru | zh | ja | nl | vi | hi | ar | Avg. | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | BM25 (Pyserini) | lexical | - | - | 18.4 | 15.8 | 15.5 | 15.3 | 15.2 | 14.9 | 13.6 | 12.4 | 11.6 | 14.1 | 14.0 | 13.6 | 13.4 | 11.1 | 14.2 |
| 2 | mono-mT5 (Bonfacio et al., 2021) | cross-encoder | 12.8M | 390M | 36.6 | 31.4 | 30.2 | 30.3 | 30.2 | 29.8 | 28.9 | 26.3 | 24.9 | 26.7 | 29.2 | 25.6 | 26.6 | 23.5 | 28.6 |
| 3 | mono-mMiniLM (Bonfacio et al., 2021) | cross-encoder | 80.0M | 107M | 36.6 | 30.9 | 29.6 | 29.1 | 28.9 | 29.3 | 27.8 | 25.1 | 24.9 | 26.3 | 27.6 | 24.7 | 26.2 | 21.9 | 27.8 |
| 4 | DPR-X (Yang et al., 2022) | single-vector | 25.6M | 550M | 24.5 | 19.6 | 18.9 | 18.3 | 19.0 | 16.9 | 18.2 | 17.7 | 14.8 | 15.4 | 18.5 | 15.1 | 15.4 | 12.9 | 17.5 |
| 5 | mE5-base (Wang et al., 2024) | single-vector | 5.1B | 278M | 35.0 | 28.9 | 30.3 | 28.0 | 27.5 | 26.1 | 27.1 | 24.5 | 22.9 | 25.0 | 27.3 | 23.9 | 24.2 | 20.5 | 26.5 |
| 6 | mColBERT (Bonfacio et al., 2021) | multi-vector | 25.6M | 180M | 35.2 | 30.1 | 28.9 | 29.2 | 29.2 | 27.5 | 28.1 | 25.0 | 24.6 | 23.6 | 27.3 | 18.0 | 23.2 | 20.9 | 26.5 |
| 7 | DPR-XM (ours) | single-vector | 25.6M | 277M | 32.7 | 23.6 | 23.5 | 22.3 | 22.7 | 22.0 | 22.1 | 19.9 | 18.1 | 18.7 | 22.9 | 18.0 | 16.0 | 15.1 | 21.3 |
| 8 | ColBERT-XM (ours) | multi-vector | 6.4M | 277M | 37.2 | 28.5 | 26.9 | 26.5 | 27.6 | 26.3 | 27.0 | 25.1 | 24.6 | 24.1 | 27.5 | 22.6 | 23.8 | 19.5 | 26.2 |
Training
Background
We use the xmod-base backbone and fine-tune it on 25.6M MS MARCO triples. We optimize the model with a contrastive learning objective: given a sentence from the pair, the model should predict which out of a set of randomly sampled other sentences, was actually paired with it in the dataset. Formally, we compute the cos similarity from each possible sentence pairs from the batch. We then apply the cross entropy loss with a temperature of 0.05 by comparing with true pairs.
Hyperparameters
We traine the model on a single Tesla V100 GPU with 32GBs of memory for 200k steps using a batch size of 128. We use the AdamW optimizer with a peak learning rate of 2e-5 with warm up along the first 10% of training steps and linear scheduling. The sequence length was limited to 128 tokens.
Data
We use training triples from the MS MARCO passage ranking dataset, which contains 8.8M passages and 539K training queries. We sample hard negatives mined from 12 distinct dense retrievers using the msmarco-hard-negatives distillation dataset.
Citation
@article{louis2024modular,
author = {Louis, Antoine and Saxena, Vageesh and van Dijck, Gijs and Spanakis, Gerasimos},
title = {ColBERT-XM: A Modular Multi-Vector Representation Model for Zero-Shot Multilingual Information Retrieval},
journal = {CoRR},
volume = {abs/2402.xxxxx},
year = {2024},
url = {https://doi.org/},
doi = {},
eprinttype = {arXiv},
eprint = {2402.xxxxx},
}
License
DPR-XM is licensed under the Apache 2.0 license.