Pre-processing Matters! Improved Wikipedia Corpora for Open-Domain Question Answering.

@inproceedings{tamber-2023-preprocessing, author = {Manveer Singh Tamber and Ronak Pradeep and Jimmy Lin}, editor = {Jaap Kamps and Lorraine Goeuriot and Fabio Crestani and Maria Maistro and Hideo Joho and Brian Davis and Cathal Gurrin and Udo Kruschwitz and Annalina Caputo}, title = {{Pre-processing Matters! Improved Wikipedia Corpora for Open-Domain Question Answering}}, booktitle = {{Advances in Information Retrieval - 45th European Conference on Information Retrieval, ECIR 2023, Dublin, Ireland, April 2-6, 2023, Proceedings, Part III}}, series = {Lecture Notes in Computer Science}, volume = {13982}, pages = {163--176}, publisher = {Springer}, year = {2023}, url = {https://doi.org/10.1007/978-3-031-28241-6_11}, doi = {https://doi.org/10.1007/978-3-031-28241-6_11} }