Learning term weights by overfitting pairwise ranking loss

Creative Commons License

Sahin Ö., ÇİÇEKLİ İ., Ercan G.

Turkish Journal of Electrical Engineering and Computer Sciences, vol.30, no.5, pp.1914-1930, 2022 (SCI-Expanded) identifier

  • Publication Type: Article / Article
  • Volume: 30 Issue: 5
  • Publication Date: 2022
  • Doi Number: 10.55730/1300-0632.3913
  • Journal Name: Turkish Journal of Electrical Engineering and Computer Sciences
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, Applied Science & Technology Source, Compendex, Computer & Applied Sciences, INSPEC, TR DİZİN (ULAKBİM)
  • Page Numbers: pp.1914-1930
  • Keywords: Information retrieval, pairwise ranking optimization, passage ranking, term weighting
  • Hacettepe University Affiliated: Yes


© 2022 Turkiye Klinikleri. All rights reserved.A search engine strikes a balance between effectiveness and efficiency to retrieve the best documents in a scalable way. Recent deep learning-based ranker methods are proving to be effective and improving the state-of-the-art in relevancy metrics. However, as opposed to index-based retrieval methods, neural rankers like bidirectional encoder representations from transformers (BERT) do not scale to large datasets. In this article, we propose a query term weighting method that can be used with a standard inverted index without modifying it. Query term weights are learned using relevant and irrelevant document pairs for each query, using a pairwise ranking loss. The learned weights prove to be more effective than term recall which is a probabilistic relevance feedback, previously used for the task. We further show that these weights can be predicted with a BERT regression model and improve the performance of both a BM25 based index and an index already optimized with a term weighting function.