Cargando…
Rethinking Query Expansion for BERT Reranking
Recent studies have shown promising results of using BERT for Information Retrieval with its advantages in understanding the text content of documents and queries. Compared to short, keywords queries, higher accuracy of BERT were observed on long, natural language queries, demonstrating BERT’s abili...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7148061/ http://dx.doi.org/10.1007/978-3-030-45442-5_37 |
_version_ | 1783520522749870080 |
---|---|
author | Padaki, Ramith Dai, Zhuyun Callan, Jamie |
author_facet | Padaki, Ramith Dai, Zhuyun Callan, Jamie |
author_sort | Padaki, Ramith |
collection | PubMed |
description | Recent studies have shown promising results of using BERT for Information Retrieval with its advantages in understanding the text content of documents and queries. Compared to short, keywords queries, higher accuracy of BERT were observed on long, natural language queries, demonstrating BERT’s ability in extracting rich information from complex queries. These results show the potential of using query expansion to generate better queries for BERT-based rankers. In this work, we explore BERT’s sensitivity to the addition of structure and concepts. We find that traditional word-based query expansion is not entirely applicable, and provide insight into methods that produce better experimental results. |
format | Online Article Text |
id | pubmed-7148061 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2020 |
record_format | MEDLINE/PubMed |
spelling | pubmed-71480612020-04-13 Rethinking Query Expansion for BERT Reranking Padaki, Ramith Dai, Zhuyun Callan, Jamie Advances in Information Retrieval Article Recent studies have shown promising results of using BERT for Information Retrieval with its advantages in understanding the text content of documents and queries. Compared to short, keywords queries, higher accuracy of BERT were observed on long, natural language queries, demonstrating BERT’s ability in extracting rich information from complex queries. These results show the potential of using query expansion to generate better queries for BERT-based rankers. In this work, we explore BERT’s sensitivity to the addition of structure and concepts. We find that traditional word-based query expansion is not entirely applicable, and provide insight into methods that produce better experimental results. 2020-03-24 /pmc/articles/PMC7148061/ http://dx.doi.org/10.1007/978-3-030-45442-5_37 Text en © Springer Nature Switzerland AG 2020 This article is made available via the PMC Open Access Subset for unrestricted research re-use and secondary analysis in any form or by any means with acknowledgement of the original source. These permissions are granted for the duration of the World Health Organization (WHO) declaration of COVID-19 as a global pandemic. |
spellingShingle | Article Padaki, Ramith Dai, Zhuyun Callan, Jamie Rethinking Query Expansion for BERT Reranking |
title | Rethinking Query Expansion for BERT Reranking |
title_full | Rethinking Query Expansion for BERT Reranking |
title_fullStr | Rethinking Query Expansion for BERT Reranking |
title_full_unstemmed | Rethinking Query Expansion for BERT Reranking |
title_short | Rethinking Query Expansion for BERT Reranking |
title_sort | rethinking query expansion for bert reranking |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7148061/ http://dx.doi.org/10.1007/978-3-030-45442-5_37 |
work_keys_str_mv | AT padakiramith rethinkingqueryexpansionforbertreranking AT daizhuyun rethinkingqueryexpansionforbertreranking AT callanjamie rethinkingqueryexpansionforbertreranking |