Update README.md

README.md

@@ -9,7 +9,7 @@ metrics:
 tags:
 - feature-extraction
 - sentence-similarity
-library_name: colbert-ai
+library_name: colbert-ir
 inference: false
 language: 
 - multilingual
@@ -112,25 +112,25 @@ language:
   <p>
 </h4>
 
-This is a [colbert-ai](https://github.com/stanford-futuredata/ColBERT) model: it encodes queries & passages into matrices of token-level embeddings and efficiently finds passages that contextually match the query using scalable vector-similarity (MaxSim) operators. It can be used for tasks like clustering or semantic search. The model uses an [XMOD](https://huggingface.co/facebook/xmod-base) 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.
+This is a [colbert-ir](https://github.com/stanford-futuredata/ColBERT) model: it encodes queries & passages into matrices of token-level embeddings and efficiently finds passages that contextually match the query using scalable vector-similarity (MaxSim) operators. It can be used for tasks like clustering or semantic search. The model uses an [XMOD](https://huggingface.co/facebook/xmod-base) 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 ColBERT-XM with [colbert-ai](#using-colbert-ai) or [RAGatouille](#using-ragatouille).
+Here are some examples for using ColBERT-XM with [colbert-ir](#using-colbert-ir) or [RAGatouille](#using-ragatouille).
 
-### Using ColBERT-AI
+### Using ColBERT-IR
 
-Start by installing the [library](https://github.com/stanford-futuredata/ColBERT) and some extra rquirements:
+Start by installing the [library](https://github.com/stanford-futuredata/ColBERT) and some extra requirements:
 
 ```
-pip install git+https://github.com/stanford-futuredata/ColBERT.git@main#egg=colbert-ai torchtorch==2.1.2 faiss-gpu==1.7.2
+pip install git+https://github.com/stanford-futuredata/ColBERT.git@main#egg=colbert-ir torchtorch==2.1.2 faiss-gpu==1.7.2 langdetect==1.0.9
 ```
 
-Using the modeel on a collection of passages typically involves the following steps:
+Using the model on a collection of passages typically involves the following steps:
 
 - **Step 1: Indexing.** This step encodes all passages into matrices, stores them on disk, and builds data structures for efficient search. (⚠️ indexing requires a GPU!)
 ```
-from colbert import Indexer
+from . import CustomIndexer # Use of a custom indexer that automatically detects the language of the passages to index and activate the language-specific adapters accordingly
 from colbert.infra import Run, RunConfig
 
 n_gpu: int = 1 # Set your number of available GPUs
@@ -138,7 +138,7 @@ experiment: str = "" # Name of the folder where the logs and created indices wil
 index_name: str = "" # The name of your index, i.e. the name of your vector database
 
 with Run().context(RunConfig(nranks=n_gpu,experiment=experiment)):
-    indexer = Indexer(checkpoint="antoinelouis/colbertv1-camembert-base-mmarcoFR")
+    indexer = CustomIndexer(checkpoint="antoinelouis/colbert-xm")
     documents = [
       "Ceci est un premier document.",
       "Voici un second document.",
@@ -150,7 +150,7 @@ with Run().context(RunConfig(nranks=n_gpu,experiment=experiment)):
 
 - **Step 2: Searching.** Given the model and index, you can issue queries over the collection to retrieve the top-k passages for each query.
 ```
-from colbert import Searcher
+from . import CustomSearcher # Use of a custom searcher that automatically detects the language of the passages to index and activate the language-specific adapters accordingly
 from colbert.infra import Run, RunConfig
 
 n_gpu: int = 0
@@ -159,7 +159,7 @@ index_name: str = "" # Name of your previously created index where the documents
 k: int = 10 # how many results you want to retrieve
 
 with Run().context(RunConfig(nranks=n_gpu,experiment=experiment)):
-    searcher = Searcher(index=index_name) # You don't need to specify checkpoint again, the model name is stored in the index.
+    searcher = CustomSearcher(index=index_name) # You don't need to specify checkpoint again, the model name is stored in the index.
     query = "Comment effectuer une recherche avec ColBERT ?"
     results = searcher.search(query, k=k)
     # results: tuple of tuples of length k containing ((passage_id, passage_rank, passage_score), ...)
@@ -168,14 +168,14 @@ with Run().context(RunConfig(nranks=n_gpu,experiment=experiment)):
 
 ### Using RAGatouille
 
-[To come...]
+[To come]
 
 ***
 
 ## Evaluation
 
 - **MS MARCO**: 
-We evaluate our model on the small development set of [MS MARCO](https://ir-datasets.com/msmarco-passage.html#msmarco-passage/dev/small), 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).
+We evaluate our model on the small development sets of [mMARCO](https://huggingface.co/datasets/unicamp-dl/mmarco), which consists of 6,980 queries for a corpus of 8.8M candidate passages in 14 languages. Below, we compared its multilingual performance with other retrieval models on the dataset official metrics, 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. |
 |---:|:----------------------------------------------------------------------------------------------------------------------------------------|:--------------|:--------:|:-------:|-----:|-----:|-----:|-----:|-----:|-----:|-----:|-----:|-----:|-----:|-----:|-----:|-----:|-----:|-----:|
@@ -189,13 +189,25 @@ We evaluate our model on the small development set of [MS MARCO](https://ir-data
 |  7 | [DPR-XM](https://huggingface.co/antoinelouis/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 |
 
+- **Mr. TyDi**:
+- We also evaluate our model on the test set of [Mr. TyDi](https://huggingface.co/datasets/castorini/mr-tydi), another multilingual open retrieval dataset including low-resource languages not present in mMARCO. Below, we compared its performance with other retrieval models on the official dataset metrics, i.e., mean reciprocal rank at cut-off 100 (MRR@100) and recall at cut-off 100 (R@100).
+
+|    | model                                                                         |          Type | #Samples | #Params |   ar |   bn |   en |   fi |   id |   ja |   ko |   ru |   sw |   te | Avg. |
+|---:|:------------------------------------------------------------------------------|:--------------|:--------:|:-------:|-----:|-----:|-----:|-----:|-----:|-----:|-----:|-----:|-----:|-----:|-----:|
+|    |                                                                               |               |          |         |      |      |      |      | **MRR@100** | |    |      |      |      |      |   
+|  1 | BM25 ([Pyserini](https://github.com/castorini/pyserini))                      |       lexical |        - |       - | 36.8 | 41.8 | 14.0 | 28.4 | 37.6 | 21.1 | 28.5 | 31.3 | 38.9 | 34.3 | 31.3 |
+|  2 | mono-mT5 ([Bonfacio et al., 2021](https://doi.org/10.48550/arXiv.2108.13897)) | cross-encoder |    12.8M |    390M | 62.2 | 65.1 | 35.7 | 49.5 | 61.1 | 48.1 | 47.4 | 52.6 | 62.9 | 66.6 | 55.1 |
+|  3 | mColBERT ([Bonfacio et al., 2021](https://doi.org/10.48550/arXiv.2108.13897)) |  multi-vector |    25.6M |    180M | 55.3 | 48.8 | 32.9 | 41.3 | 55.5 | 36.6 | 36.7 | 48.2 | 44.8 | 61.6 | 46.1 |
+|  4 | **ColBERT-XM** (ours)                                                         |  multi-vector |     6.4M |    277M | 55.2 | 56.6 | 36.0 | 41.8 | 57.1 | 42.1 | 41.3 | 52.2 | 56.8 | 50.6 | 49.0 |
+|    |                                                                               |               |          |         |      |      |      |      | **R@100** | |      |      |      |      |      |   
+
 ***
 
 ## Training
 
 #### Data
 
-We use the training samples from the [MS MARCO passage ranking](https://ir-datasets.com/msmarco-passage.html#msmarco-passage/train) dataset, which 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](https://huggingface.co/datasets/sentence-transformers/msmarco-hard-negatives) distillation dataset. Our final training set consists of 6.4M (q, p+, p-) triples.
+We use the English training samples from the [MS MARCO passage ranking](https://ir-datasets.com/msmarco-passage.html#msmarco-passage/train) dataset, which 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](https://huggingface.co/datasets/sentence-transformers/msmarco-hard-negatives) distillation dataset. Our final training set consists of 6.4M (q, p+, p-) triples.
 
 #### Implementation