Skip to content

Commit

Permalink
Update README.md
Browse files Browse the repository at this point in the history
  • Loading branch information
@xhluca
xhluca authored Aug 20, 2024
1 parent 4208b86 commit daf29ce
Showing 1 changed file with 5 additions and 0 deletions.
5 changes: 5 additions & 0 deletions README.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -360,6 +360,11 @@ When testing with 6 arbitrary queries with an index built with MS MARCO (8.8M do

When you run `bm25s` on 1000 queries on the Natural Questions dataset (2M+ documents), the memory usage is over 50% lower than the in-memory version with trivial difference in speed. You can find more information in the [GitHub repository](https://github.com/xhluca/bm25s).

## Acknowledgement

* The multilingual stopwords are sourced from the [NLTK stopwords lists](https://github.com/nltk/nltk/blob/96ee715997e1c8d9148b6d8e1b32f412f31c7ff7/nltk/corpus/__init__.py#L315).
* The numba implementation are inspired by numba implementations originally proposed by [baguetter](https://github.com/mixedbread-ai/baguetter) and [retriv](https://github.com/AmenRa/retriv).

## Citation

If you use `bm25s` in your work, please use the following bibtex:
Expand Down

0 comments on commit daf29ce

Please sign in to comment.