NLP Bi-Encoder和Re-ranker

Retrieve & Re-Rank

https://www.sbert.net/examples/applications/retrieve_rerank/README.html

Bi-Encoder vs. Cross-Encoder

https://www.sbert.net/examples/applications/cross-encoder/README.html

Bi-Encoder会用BERT对输入文本编码，再根据cosine相似度分数筛选文本。Cross-Encoder会直接计算两个句子的相关性分数。

如何将BI和Cross Encoder配合使用？可以先用BI-Encoder选出top 100个候选项，再用Cross-Encoder挑选最佳选项。

Combining Bi- and Cross-Encoders

Cross-Encoder achieve higher performance than Bi-Encoders, however, they do not scale well for large datasets.

Here, it can make sense to combine Cross- and Bi-Encoders, for example in Information Retrieval / Semantic Search scenarios:

First, you use an efficient Bi-Encoder to retrieve e.g. the top-100 most similar sentences for a query.

Then, you use a Cross-Encoder to re-rank these 100 hits by computing the score for every (query, hit) combination.