Soomin Lee
ABSTRACT
To help customers who are still in the exploration phase, Web search engines and e-commerce websites often provide relevant Q&As in widgets, such as ‘People Also Ask’ and ‘Customers Also Ask Alexa’, with additional information. In this work, we propose to enrich this customer experience by rendering related products under each Q&A based on an automated online query recommendation. We define what are the tenets for high-quality query recommendations and explain why this challenge is different from the existing query re-writing, query expansion and keyphrase generation methods. We describe a data collection method which uses customer co-click information on a proprietary website in order to successfully guide our model into generating query recommendations that satisfy all tenets. Offline and online evaluation results demonstrate that our proposed approach generates superior query recommendations and brings much more customer engagement over strong baselines.
- Wasi Ahmad, Xiao Bai, Soomin Lee, and Kai-Wei Chang. 2021. Select, Extract and Generate: Neural Keyphrase Generation with Layer-wise Coverage Attention. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). Association for Computational Linguistics, Online, 1389–1404. https://doi.org/10.18653/v1/2021.acl-long.111Google Scholar
Cross Ref
- AI21-Studio. 2023. Jurassic-2 Models. https://docs.ai21.com/docs/jurassic-2-models.Google Scholar
- James Allan. 1995. Relevance Feedback With Too Much Data. In Proc. of SIGIR. ACM Press, 337–343.Google Scholar
- Omar Alonso, Sushma Bannur, Kartikay Khandelwal, and Shankar Kalyanaraman. 2015. The World Conversation: Web Page Metadata Generation From Social Sources. In Proc. of WWW. 385–395.Google ScholarDigital Library
- Hiteshwar Kumar Azad and Akshay Deepak. 2019. Query expansion techniques for information retrieval: A survey. Inf. Process. Manag. 56, 5 (2019), 1698–1735.Google ScholarDigital Library
- Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2014. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473.Google Scholar
- Steven Bird, Ewan Klein, and Edward Loper. 2009. Natural language processing with Python: analyzing text with the natural language toolkit. " O’Reilly Media, Inc.".Google ScholarDigital Library
- Ilaria Bordino, Gianmarco De Francisci Morales, Ingmar Weber, and Francesco Bonchi. 2013. From Machu picchu to "Rafting the Urubamba River": Anticipating Information Needs via the Entity-Query Graph. In Proc. of WSDM. 275–284.Google Scholar
- David Carmel, Yaroslav Fyodorov, Saar Kuzi, Avihai Mejer, Fiana Raiber, and Elad Rainshmidt. 2019. Enriching News Articles with Related Search Queries. In The World Wide Web Conference. 162–172.Google Scholar
- Zhicong Cheng, Bin Gao, and Tie-Yan Liu. 2010. Actively Predicting Diverse Search Intent from User Browsing Behaviors. In Proc. of WWW. 221–230.Google ScholarDigital Library
- K.-W. Chang D. Wu, W. U. Ahmad. 2022. Pre-trained Language Models for Keyphrase Generation: A Thorough Empirical Study. arxiv:2212.10233 [cs.CL]Google Scholar
- J. Gu et al.2016. Incorporating Copying Mechanism in Sequence-to-Sequence Learning. In Proc. of ACL. Association for Computational Linguistics, 1631–1640.Google Scholar
- Donna Harman. 1988. Towards Interactive Query Expansion. In Proc. of SIGIR. ACM, 321–331.Google ScholarDigital Library
- Mohammad Al Hasan, Nish Parikh, Gyanit Singh, and Neel Sundaresan. 2011. Query Suggestion for E-Commerce Sites. In Proc. of WSDM. 765–774.Google ScholarDigital Library
- Matthew Honnibal and Ines Montani. 2017. spaCy 2: Natural language understanding with Bloom embeddings, convolutional neural networks and incremental parsing. (2017). To appear.Google Scholar
- Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In 3rd International Conference on Learning Representations, ICLR, Yoshua Bengio and Yann LeCun (Eds.).Google Scholar
- Weize Kong, Rui Li, Jie Luo, Aston Zhang, Yi Chang, and James Allan. 2015. Predicting Search Intent Based on Pre-Search Context. In Proc. of SIGIR. 503–512.Google ScholarDigital Library
- Mayank Kulkarni, Debanjan Mahata, Ravneet Arora, and Rajarshi Bhowmik. 2022. Learning Rich Representation of Keyphrases from Text. In Findings of the Association for Computational Linguistics: NAACL 2022. Association for Computational Linguistics, 891–906.Google ScholarCross Ref
- Chia-Jung Lee and W. Bruce Croft. 2012. Generating Queries from User-Selected Text. In Proc. of IIIX. 100–109.Google ScholarDigital Library
- Yen-Chieh Lien, Rongting Zhang, Max Harper, Vanessa Murdock, and Chia-Jung Lee. 2022. Leveraging customer reviews for e-commerce query generation. In Proc. of ECIR 2022.Google ScholarDigital Library
- Chin-Yew Lin. 2004. ROUGE: A Package for Automatic Evaluation of Summaries. In Text Summarization Branches Out. ACL, Barcelona, Spain, 74–81.Google Scholar
- Rui Meng, Sanqiang Zhao, Shuguang Han, Daqing He, Peter Brusilovsky, and Yu Chi. 2017. Deep Keyphrase Generation. In Proc. of ACL. Association for Computational Linguistics, 582–592.Google ScholarCross Ref
- Ron Mittelhammer, George Judge, and Douglas Miller. 2002. Econometric Foundation. Vol. 97.Google Scholar
- Seung-Taek Park, David M. Pennock, C. Lee Giles, and Robert Krovetz. 2004. Analysis of Lexical Signatures for Improving Information Persistence on the World Wide Web. ACM Trans. Inf. Syst. 22, 4 (oct 2004), 540–572.Google ScholarDigital Library
- Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2019. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. CoRR abs/1910.10683 (2019).Google Scholar
- Nils Reimers and Iryna Gurevych. 2019. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics. https://arxiv.org/abs/1908.10084Google ScholarCross Ref
- Gerard Salton and Chris Buckley. 1990. Improving retrieval performance by relevance feedback. J. Am. Soc. Inf. Sci. 41, 4 (1990), 288–297.Google ScholarCross Ref
- Eilon Sheetrit, Yaroslav Fyodorov, Fiana Raiber, and Oren Kurland. 2021. Recommending Search Queries in Documents Using Inter N-Gram Similarities. In Proc. of ICTIR. 211–220.Google ScholarDigital Library
- Eilon Sheetrit, Fiana Raiber, and Oren Kurland. 2023. Entity-Based Relevance Feedback for Document Retrieval. In Proc. of ICTIR. 177–187.Google ScholarDigital Library
- Mingyang Song, Yi Feng, and Liping Jing. 2023. A Survey on Recent Advances in Keyphrase Extraction from Pre-trained Language Models. 2153–2164.Google Scholar
- Amanda Spink. 1994. Term Relevance Feedback and Query Expansion: Relation to Design. In Proc. of SIGIR. 81–90.Google ScholarCross Ref
- Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le, Ed Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2023. Self-Consistency Improves Chain of Thought Reasoning in Language Models. arxiv:2203.11171 [cs.CL]Google Scholar
- Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Ed H. Chi, Quoc Le, and Denny Zhou. 2022. Chain of Thought Prompting Elicits Reasoning in Large Language Models. CoRR abs/2201.11903 (2022).Google Scholar
- Di Wu, Wasi Uddin Ahmad, and Kai-Wei Chang. 2022. Pre-trained Language Models for Keyphrase Generation: A Thorough Empirical Study. arxiv:2212.10233 [cs.CL]Google Scholar
- Lee Xiong, Chuan Hu, Chenyan Xiong, Daniel Campos, and Arnold Overwijk. 2019. Open Domain Web Keyphrase Extraction Beyond Language Modeling. In Proc. of EMNLP. 5175–5184.Google ScholarCross Ref
- Jinxi Xu and W. Bruce Croft. 1996. Query Expansion Using Local and Global Document Analysis. In Proc. of SIGIR. 4–11.Google ScholarDigital Library
- Jiacheng Ye, Tao Gui, Yichao Luo, Yige Xu, and Qi Zhang. 2021. One2Set: Generating Diverse Keyphrases as a Set. In Proc. of ACL. 4598–4608.Google ScholarCross Ref
- Xingdi Yuan, Tong Wang, Rui Meng, Khushboo Thaker, Peter Brusilovsky, Daqing He, and Adam Trischler. 2020. One Size Does Not Fit All: Generating and Evaluating Variable Number of Keyphrases. In Proc. of ACL. 7961–7975.Google ScholarCross Ref
Index Terms
- Product Query Recommendation for Enriching Suggested Q&As
Recommendations
Task-aware query recommendation
SIGIR '13: Proceedings of the 36th international ACM SIGIR conference on Research and development in information retrievalWhen generating query recommendations for a user, a natural approach is to try and leverage not only the user's most recently submitted query, or reference query, but also information about the current search context, such as the user's recent search ...
A hybrid recommendation system for Q&A documents
Highlights- A hybrid recommendation system for Q&A documents is proposed.
- Current knowledge ...
AbstractQuestion and answer (Q&A) documents are a new type of knowledge document composed of a question part and an answer part. The questions represent knowledge needs, and the answers contain the knowledge that meets these knowledge needs. ...
Product recommendation approaches: Collaborative filtering via customer lifetime value and customer demands
Recommender systems are techniques that allow companies to develop one-to-one marketing strategies and provide support in connecting with customers for e-commerce. There exist various recommendation techniques, including collaborative filtering (CF), ...
Comments