ABSTRACT
Query reformulation is a key mechanism to alleviate the linguistic chasm of query in ad-hoc retrieval. Among various solutions, query reduction effectively removes extraneous terms and specifies concise user intent from long queries. However, it is challenging to capture hidden and diverse user intent. This paper proposes Contextualized Query Reduction (ConQueR) using a pre-trained language model (PLM). Specifically, it reduces verbose queries with two different views: core term extraction and sub-query selection. One extracts core terms from an original query at the term level, and the other determines whether a sub-query is a suitable reduction for the original query at the sequence level. Since they operate at different levels of granularity and complement each other, they are finally aggregated in an ensemble manner. We evaluate the reduction quality of ConQueR on real-world search logs collected from a commercial web search engine. It achieves up to 8.45% gains in exact match scores over the best competing model.
- Yuki Amemiya, Tomohiro Manabe, Sumio Fujita, and Tetsuya Sakai. 2021. How Do Users Revise Zero-Hit Product Search Queries?. In ECIR. 185--192.Google Scholar
- Peter G. Anick. 2003. Using terminological feedback for web search refinement: a log-based study. In SIGIR. 88--95.Google Scholar
- Hiteshwar Kumar Azad and Akshay Deepak. 2019. Query expansion techniques for information retrieval: A survey. Inf. Process. Manag., Vol. 56, 5 (2019), 1698--1735.Google ScholarDigital Library
- Michael Bendersky and W. Bruce Croft. 2008. Discovering Key Concepts in Verbose Queries. In SIGIR. 491--498.Google Scholar
- Michael Bendersky, Donald Metzler, and W. Bruce Croft. 2011. Parameterized Concept Weighting in Verbose Queries. In SIGIR. 605--614.Google Scholar
- Kaibo Cao, Chunyang Chen, Sebastian Baltes, Christoph Treude, and Xiang Chen. 2021. Automated Query Reformulation for Efficient Search based on Query Logs From Stack Overflow. In ICSE. 1273--1285.Google Scholar
- Claudio Carpineto and Giovanni Romano. 2012. A Survey of Automatic Query Expansion in Information Retrieval. ACM Comput. Surv., Vol. 44, 1 (2012), 1:1--1:50.Google ScholarDigital Library
- Messaoud Chaa, Omar Nouali, and Patrice Bellot. 2016. Verbose Query Reduction by Learning to Rank for Social Book Search Track. In CLEF (CEUR Workshop Proceedings). 1072--1078.Google Scholar
- Junyoung Chung, Caglar Gülcehre, KyungHyun Cho, and Yoshua Bengio. 2014. Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling. CoRR (2014).Google Scholar
- Kevin Clark, Minh-Thang Luong, Quoc V. Le, and Christopher D. Manning. 2020. ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators. In ICLR.Google Scholar
- Charles L. A. Clarke, Nick Craswell, Ian Soboroff, and Gordon V. Cormack. 2010. Overview of the TREC 2010 Web Track. In TREC, Vol. 500--294.Google Scholar
- Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-HLT. 4171--4186.Google Scholar
- Manish Gupta and Michael Bendersky. 2015. Information Retrieval with Verbose Queries. In SIGIR. 1121--1124.Google Scholar
- Kishaloy Halder, Heng-Tze Cheng, Ellie Ka In Chio, Georgios Roumpos, Tao Wu, and Ritesh Agarwal. 2020. Modeling Information Need of Users in Search Sessions. CoRR (2020).Google Scholar
- Rosie Jones and Daniel C. Fain. 2003. Query word deletion prediction. In SIGIR. 435--436.Google Scholar
- Jürgen Koenemann and Nicholas J. Belkin. 1996. A Case for Interaction: A Study of Interactive Information Retrieval Behavior and Effectiveness. In CHI. 205--212.Google Scholar
- Bevan Koopman, Liam Cripwell, and Guido Zuccon. 2017. Generating Clinical Queries from Patient Narratives: A Comparison between Machines and Humans. In SIGIR. 853--856.Google Scholar
- Giridhar Kumaran and Vitor R. Carvalho. 2009. Reducing long queries using query quality predictors. In SIGIR. 564--571.Google Scholar
- Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Veselin Stoyanov, and Luke Zettlemoyer. 2020. BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. In ACL. 7871--7880.Google Scholar
- K. Tamsin Maxwell and W. Bruce Croft. 2013. Compact query term selection using topically related text. In SIGIR. 583--592.Google Scholar
- Shahrzad Naseri, Jeff Dalton, Andrew Yates, and James Allan. 2021. CEQE: Contextualized Embeddings for Query Expansion. In ECIR, Vol. 12656. 467--482.Google Scholar
- Rodrigo Nogueira and Kyunghyun Cho. 2019. Passage Re-ranking with BERT. CoRR (2019).Google Scholar
- Jessie Ooi, Xiuqin Ma, Hongwu Qin, and Siau Chuin Liew. 2015. A survey of query expansion, query suggestion and query refinement techniques. In ICSECS. IEEE, 112--117.Google Scholar
- Greg Pass, Abdur Chowdhury, and Cayley Torgeson. 2006. A picture of search. In Infoscale. 1.Google Scholar
- Alec Radford, Jeff Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. 2019. Language Models are Unsupervised Multitask Learners. (2019).Google Scholar
- Eldar Sadikov, Jayant Madhavan, Lu Wang, and Alon Y. Halevy. 2010. Clustering query refinements by user intent. In WWW. 841--850.Google Scholar
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In NeurIPS. 5998--6008.Google Scholar
- Bienvenido Vé lez, Ron Weiss, Mark A. Sheldon, and David K. Gifford. 1997. Fast and Effective Query Refinement. In SIGIR. 6--15.Google Scholar
- Wenjie Wang, Fuli Feng, Xiangnan He, Liqiang Nie, and Tat-Seng Chua. 2021. Denoising Implicit Feedback for Recommendation. In WSDM. 373--381.Google Scholar
- Xiaobing Xue, Samuel J. Huston, and W. Bruce Croft. 2010. Improving verbose queries using subset distribution. In CIKM. 1059--1068.Google Scholar
- Bishan Yang, Nish Parikh, Gyanit Singh, and Neel Sundaresan. 2014. A Study of Query Term Deletion Using Large-Scale E-commerce Search Logs. In ECIR. 235--246.Google Scholar
- Peilin Yang and Hui Fang. 2017. Can Short Queries Be Even Shorter?. In ICTIR. 43--50.Google Scholar
- Zhi Zheng, Kai Hui, Ben He, Xianpei Han, Le Sun, and Andrew Yates. 2020. BERT-QE: Contextualized Query Expansion for Document Re-ranking. In Findings of ACL. 4718--4728.Google Scholar
- Ingrid Zukerman, Bhavani Raskutti, and Yingying Wen. 2003. Query Expansion and Query Reduction in Document Retrieval. In ICTAI. 552--559.Google Scholar
Index Terms
- ConQueR: Contextualized Query Reduction using Search Logs
Recommendations
Information Retrieval with Verbose Queries
SIGIR '15: Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information RetrievalRecently, the focus of many novel search applications shifted from short keyword queries to verbose natural language queries. Examples include question answering systems and dialogue systems, voice search on mobile devices and entity search engines like ...
Analyzing and evaluating query reformulation strategies in web search logs
CIKM '09: Proceedings of the 18th ACM conference on Information and knowledge managementUsers frequently modify a previous search query in hope of retrieving better results. These modifications are called query reformulations or query refinements. Existing research has studied how web search engines can propose reformulations, but has ...
Intent Term Weighting in E-commerce Queries
CIKM '19: Proceedings of the 28th ACM International Conference on Information and Knowledge ManagementE-commerce search engines can fail to retrieve results that satisfy a query's product intent because: (i) conventional retrieval approaches, such as BM25, may ignore the important terms in queries owing to their low "inverse document frequency" " (IDF), ...
Comments