Update README.md
Browse files
README.md
CHANGED
|
@@ -108,7 +108,7 @@ language:
|
|
| 108 |
</h4>
|
| 109 |
|
| 110 |
|
| 111 |
-
This is a **multilingual**
|
| 112 |
pair and outputs a relevance score between 0 and 1. The model should be used as a reranker for semantic search: given a query, encode the latter with some candidate
|
| 113 |
passages -- e.g., retrieved with BM25 or a bi-encoder -- then sort the passages in a decreasing order of relevance according to the model's predictions.
|
| 114 |
The model uses an [XMOD](https://huggingface.co/facebook/xmod-base) backbone, which allows it to learn from monolingual fine-tuning
|
|
|
|
| 108 |
</h4>
|
| 109 |
|
| 110 |
|
| 111 |
+
This is a **multilingual** cross-encoder model. It performs cross-attention between a question-passage
|
| 112 |
pair and outputs a relevance score between 0 and 1. The model should be used as a reranker for semantic search: given a query, encode the latter with some candidate
|
| 113 |
passages -- e.g., retrieved with BM25 or a bi-encoder -- then sort the passages in a decreasing order of relevance according to the model's predictions.
|
| 114 |
The model uses an [XMOD](https://huggingface.co/facebook/xmod-base) backbone, which allows it to learn from monolingual fine-tuning
|