maidalun1020
commited on
Commit
•
09f1802
1
Parent(s):
83860f2
Update README.md
Browse files
README.md
CHANGED
@@ -38,7 +38,7 @@ language:
|
|
38 |
- 中英日韩四个语种,以及中英日韩四个语种的跨语种能力(Multilingual and Crosslingual capability in English, Chinese, Japanese and Korean);
|
39 |
- RAG优化,适配更多真实业务场景(RAG adaptation for more domains, including Education, Law, Finance, Medical, Literature, FAQ, Textbook, Wikipedia, etc.);
|
40 |
- <a href="https://github.com/netease-youdao/BCEmbedding">BCEmbedding</a>适配长文本做rerank(Handle long passages reranking more than 512 limit in <a href="https://github.com/netease-youdao/BCEmbedding">BCEmbedding</a>);
|
41 |
-
- RerankerModel可以提供 **“平滑”的“绝对”相关性分数**,**“平滑”对排序友好**,**“绝对”分数用于过滤低质量passage
|
42 |
- **最佳实践(Best practice)** :embedding召回top50-100片段,reranker对这50-100片段精排,最后取top5-10片段。(1. Get top 50-100 passages with [bce-embedding-base_v1](https://huggingface.co/maidalun1020/bce-embedding-base_v1) for "`recall`"; 2. Rerank passages with [bce-reranker-base_v1](https://huggingface.co/maidalun1020/bce-reranker-base_v1) and get top 5-10 for "`precision`" finally. )
|
43 |
|
44 |
## News:
|
|
|
38 |
- 中英日韩四个语种,以及中英日韩四个语种的跨语种能力(Multilingual and Crosslingual capability in English, Chinese, Japanese and Korean);
|
39 |
- RAG优化,适配更多真实业务场景(RAG adaptation for more domains, including Education, Law, Finance, Medical, Literature, FAQ, Textbook, Wikipedia, etc.);
|
40 |
- <a href="https://github.com/netease-youdao/BCEmbedding">BCEmbedding</a>适配长文本做rerank(Handle long passages reranking more than 512 limit in <a href="https://github.com/netease-youdao/BCEmbedding">BCEmbedding</a>);
|
41 |
+
- RerankerModel可以提供 **“平滑”的“绝对”相关性分数**,**“平滑”对排序友好**,**“绝对”分数用于过滤低质量passage**,低质量passage过滤阈值推荐0.35或0.4。(RerankerModel provides **"smooth" (for reranking) and "meaningful" (for filtering bad passages with a threshold of 0.35 or 0.4) similarity score**, which help you figure out how relavent the query and passages are!)
|
42 |
- **最佳实践(Best practice)** :embedding召回top50-100片段,reranker对这50-100片段精排,最后取top5-10片段。(1. Get top 50-100 passages with [bce-embedding-base_v1](https://huggingface.co/maidalun1020/bce-embedding-base_v1) for "`recall`"; 2. Rerank passages with [bce-reranker-base_v1](https://huggingface.co/maidalun1020/bce-reranker-base_v1) and get top 5-10 for "`precision`" finally. )
|
43 |
|
44 |
## News:
|