Abstract
Embedding-based retrieval has drawn massive attention in online search engines because of its semantic solid feature expression ability. Deep Siamese models leverage the powerful dense embeddings from strong language models like BERT to better represent sentences (queries and documents). However, deep Siamese models can suffer from a sub-optimal relevance prediction since they can hardly identify keywords due to late interaction between the query and document. Although some studies tried to adjust weights in semantic vectors by inserting some global pre-computed prior knowledge, like TF-IDF or BM25 scores, they neglected the influence of contextual information on keywords in sentences. To retrieve better-matched documents, it is necessary to identify the keywords in queries and documents accurately. To achieve this goal, we introduce a keyword identification model to detect the keywords from queries and documents automatically. Furthermore, we propose a novel multi-task framework that jointly trains both the deep Siamese model and the keywords identification model to help improve each other’s performance. We also conduct comprehensive experiments on both online A/B tests and two famous offline benchmarks to demonstrate the significant advantages of our method over other competitive baselines.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
We don’t compare with other baselines listed in the Sect. 2 since they are not open-sourced or fine-tuned for different retrieval scenarios.
References
Cer, D., et al.: Universal sentence encoder. arXiv (2018)
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv (2018)
Fan, M., Guo, J., Zhu, S., Miao, S., Sun, M., Li, P.: Mobius: towards the next generation of query-ad matching in baidu’s sponsored search. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 2509–2517 (2019)
Guo, J., Fan, Y., Ai, Q., Croft, W.B.: A deep relevance matching model for ad-hoc retrieval. In: Proceedings of the 25th ACM International on Conference on Information and Knowledge Management, pp. 55–64 (2016)
Hu, B., Lu, Z., Li, H., Chen, Q.: Convolutional neural network architectures for matching natural language sentences. In: Advances in Neural Information Processing Systems, pp. 2042–2050 (2014)
Huang, C., Liu, Q., Chen, Y.Y., et al.: Local feature descriptor learning with adaptive siamese network. arXiv (2017)
Huang, J.T., et al.: Embedding-based retrieval in facebook search. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 2553–2561 (2020)
Huang, P.S., He, X., Gao, J., Deng, L., Acero, A., Heck, L.: Learning deep structured semantic models for web search using clickthrough data. In: Proceedings of the 22nd ACM International Conference on Information & Knowledge Management, pp. 2333–2338 (2013)
Jawahar, G., Sagot, B., Seddah, D.: What does bert learn about the structure of language? In: ACL 2019–57th Annual Meeting of the Association for Computational Linguistics (2019)
Khattab, O., Zaharia, M.: Colbert: efficient and effective passage search via contextualized late interaction over bert. In: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 39–48 (2020)
Klyuev, V., Oleshchuk, V.: Semantic retrieval: an approach to representing, searching and summarising text documents. Int. J. Inf. Technol. Commun. Convergence 1(2), 221–234 (2011)
Kuang, M., Wang, W., Chen, Z., Kang, L., Yan, Q.: Efficient two-stage label noise reduction for retrieval-based tasks. In: Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining, pp. 526–534 (2022)
Lu, W., Jiao, J., Zhang, R.: Twinbert: distilling knowledge to twin-structured compressed bert models for large-scale retrieval. In: Proceedings of the 29th ACM International Conference on Information & Knowledge Management, CIKM 2020, pp. 2645–2652. Association for Computing Machinery, New York (2020)
Luan, Y., Eisenstein, J., Toutanova, K., Collins, M.: Sparse, dense, and attentional representations for text retrieval. Trans. Assoc. Comput. Linguist. 9, 329–345 (2021)
Mitra, B., Craswell, N., et al.: An introduction to neural information retrieval. Now Foundations and Trends (2018)
Nguyen, T., et al.: Ms marco: a human generated machine reading comprehension dataset. In: CoCo@ NIPS (2016)
Palangi, H., et al.: Semantic modelling with long-short-term memory for information retrieval. arXiv (2014)
Reimers, N., Gurevych, I.: Sentence-bert: sentence embeddings using siamese bert-networks. arXiv (2019)
Robertson, S., Zaragoza, H.: The Probabilistic Relevance Framework: BM25 and Beyond. Now Publishers Inc., Norwell (2009)
Salton, G., Buckley, C.: Term-weighting approaches in automatic text retrieval. Inf. Process. Manag. 24(5), 513–523 (1988)
Shan, X., et al.: Glow: global weighted self-attention network for web search. arXiv (2020)
Shan, X., et al.: Glow : global weighted self-attention network for web search. In: 2021 IEEE International Conference on Big Data (Big Data), pp. 519–528 (2021)
Shen, Y., He, X., Gao, J., Deng, L., Mesnil, G.: A latent semantic model with convolutional-pooling structure for information retrieval. In: Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management, pp. 101–110 (2014)
Sun, X., Tang, H., Zhang, F., Cui, Y., Jin, B., Wang, Z.: Table: a task-adaptive bert-based listwise ranking model for document retrieval. In: Proceedings of the 29th ACM International Conference on Information & Knowledge Management, pp. 2233–2236 (2020)
Xiong, L., et al.: Approximate nearest neighbor negative contrastive learning for dense text retrieval. arXiv (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Kuang, M. et al. (2023). Multi-task Learning Based Keywords Weighted Siamese Model for Semantic Retrieval. In: Kashima, H., Ide, T., Peng, WC. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2023. Lecture Notes in Computer Science(), vol 13937. Springer, Cham. https://doi.org/10.1007/978-3-031-33380-4_7
Download citation
DOI: https://doi.org/10.1007/978-3-031-33380-4_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-33379-8
Online ISBN: 978-3-031-33380-4
eBook Packages: Computer ScienceComputer Science (R0)