Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.
Pyserini is primarily designed to provide effective, reproducible, and easy-to-use first-stage retrieval in a multi-stage ranking architecture
Significant research has explored bias and fairness issues with language models (see, e.g.,
Sheng et al. (2021) and
Bender et al. (2021)). Predictions generated by the model may include disturbing and harmful stereotypes across protected classes; identity characteristics; and sensitive, social, and occupational groups.
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
The model creators note in the
associated Paper that:
Carbon emissions can be estimated using the
Machine Learning Impact calculator presented in
Lacoste et al. (2019).
For bag-of-words sparse retrieval, we have built in Anserini (written in Java) custom parsers and ingestion pipelines for common document formats used in IR research,
1
2@INPROCEEDINGS{Lin_etal_SIGIR2021_Pyserini,
3 author = "Jimmy Lin and Xueguang Ma and Sheng-Chieh Lin and Jheng-Hong Yang and Ronak Pradeep and Rodrigo Nogueira",
4 title = "{Pyserini}: A {Python} Toolkit for Reproducible Information Retrieval Research with Sparse and Dense Representations",
5 booktitle = "Proceedings of the 44th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2021)",
6 year = 2021,
7 pages = "2356--2362",
8}
Castorini in collaboration with Ezi Ozoani and the Hugging Face team.
Use the code below to get started with the model.
