融合关键概念和潜在概念的冗长查询缩略方法

Method for verbose queries reduction by integrating key and latent concepts

摘要

查询缩略旨在通过简化和精炼冗长的查询输入,保留其中的关键信息来提升检索结果的召回率和准确率。然而,传统方法通常是基于统计或基于预训练模型来提取冗长查询中的关键词作为检索输入,难以应对查询的复杂性(如同义词和多义词),且在保留查询核心内容时容易丢失关键信息。针对以上问题,提出一种融合关键概念和潜在概念的冗长查询缩略方法,将代表查询核心内容的关键概念和对理解查询重要但未明确表达的潜在概念相结合,从而生成更完整和有效的查询。具体而言,首先利用预训练模型来生成简短有效的查询作为关键概念,然后使用伪相关反馈方法从原始查询的相关文档集中挖掘潜在概念,最后,将两者聚合作为最终的查询缩略结果,实现冗长查询检索。实验结果表明,在Robust2004数据集上使用密集检索模型评估时,相比基线模型,文中提出的方法在R@1000和NDCG@10两个指标上分别提高2.1%和3.6%。

Abstract

Query reduction aims to enhance retrieval recall and precision by simplifying and condensing lengthy queries while retaining key information. Traditional methods often rely on statistical approaches or pre-trained models to extract keywords from lengthy queries for retrieval input. However, these methods struggle with query complexity (e.g., synonym and polyseme) and often lose crucial information. To address these issues, a method integrating key concepts and latent concepts for verbose query reduction is proposed. This approach integrates key concepts representing the core content of the query with latent concepts crucial for query understanding but not explicitly expressed to generate more comprehensive and effective queries. Specifically, pre-trained models generate concise and effective queries as key concepts, while pseudo-relevance feedback methods extract latent concepts from relevant document sets of the original query. Finally, both are combined to form the query reduction for improved retrieval. Experimental results on the Robust2004 dataset using a dense retrieval model show that the proposed method improves R@1000 and NDCG@10 by 2.1% and 3.6%, respectively, compared to baseline models.

关键词

信息检索 / 冗长查询 / 查询缩略 / 关键概念 / 潜在概念

Key words

information retrieval / verbose query / query reduction / key concept / latent concept

参考文献

[1] KIM H, CHOI M, LEE S, et al. ConQueR: contextualized query reduction using search logs[C]// Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval. Taipei: ACM, 2023: 1899-1903.

[2] CAMPOS R, MANGARAVITE V, PASQUALI A, et al. YAKE! Keyword extraction from single documents using multiple local features[J]. Information Sciences, 2020, 509: 257-289.

[3] DEVLIN J, CHANG M—W, LEE K, et al. BERT: pre—training of deep bidirectional transformers for language understanding[C]// Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Minneapolis: ACL, 2019: 4171-4186.

[4] RAFFEL C, SHAZEER N, ROBERTS A, et al. Exploring the limits of transfer learning with a unified text—to—text transformer[J]. Journal of Machine Learning Research, 2020, 21(140): 1-67.

[5] HUSTON S, CROFT W B. Evaluating verbose query processing techniques[C]// Proceedings of the 33rd International ACM SIGIR Conference on Research and Development in Information Retrieval. Shanghai: ACM, 2010: 291-298.

[6] CHAA M, NOUALI O, BELLOT P. New technique to deal with verbose queries in social book search[C]// Proceedings of the International Conference on Web Intelligence. Jinan: IEEE, 2017: 799-806.

[7] KUMARAN G, CARVALHO V R. Reducing long queries using query quality predictors[C]// Proceedings of the 32nd International ACM SIGIR Conference on Research and Development in Information Retrieval. Fuji: ACM, 2009: 564-571.

[8] ROUSSEAU F, VAZIRGIANNIS M. Main core retention on graph—of—words for single—document keyword extraction[C]// Advances in Information Retrieval: 37th European Conference on IR Research. Vienna: Springer, 2015: 382-393.

[9] BOUGOUIN A, BOUDIN F, DAILLE B. Topicrank: graph—based topic ranking for keyphrase extraction[C]// International Joint Conference on Natural Language Processing (IJCNLP). Nagoya: ACL, 2013: 543-551.

[10] PODDER D, PAIK J H, MITRA P. Neural language model based attentive term dependence model for verbose query (student abstract)[C]// Proceedings of the AAAI Conference on Artificial Intelligence. Washington: AAAI, 2023: 16300-16301.

[11] PRIYANSHU A, VIJAY S. AdaptKeyBERT: an attention—based approach towards few—shot & zero—shot domain adaptation of keybert[EB/OL]. (2022—11—16)[2024—09—15]. https://arxiv.org/abs/2211.07499.

[12] VASWANI A. Attention is all you need[C]// Advances in Neural Information Processing Systems. Long Beach: NIPS, 2017: 1-15.

[13] KHATTAB O, ZAHARIA M. Colbert: efficient and effective passage search via contextualized late interaction over BERT[C]// Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. Seattle: ACM, 2020: 39-48.

[14] VOORHEES E M. Overview of the TREC 2004 robust track[C]// Text Retrieval Conference. Washington: NIST, 2004: 1-12.

[15] ZHAI C, LAFFERTY J. Model—based feedback in the language modeling approach to information retrieval[C]// Proceedings of the Tenth International Conference on Information and Knowledge Management. Atlanta: ACM, 2001: 403-410.

[16] YU H C, XIONG C, CALLAN J. Improving query representations for dense retrieval with pseudo relevance feedback[C]// Proceedings of the 30th ACM International Conference on Information & Knowledge Management. Seattle: ACM, 2021: 3592-3596.

[17] KINGMA D P, BA J. Adam: a method for stochastic optimization[EB/OL]. (2015—07—23)[2024—09—15]. https://arxiv.org/abs/1412.6980.

[18] JIN Xiaobo, GENG Guanggang, XIE Guosen, et al. Approximately optimizing NDCG using pair—wise loss[J]. Information Sciences, 2018, 453: 50-65.

[19] GROS D, HABERMANN T, KIRSTEIN G, et al. Anaphora resolution: analysing the impact on mean average precision and detecting limitations of automated approaches[J]. International Journal of Information Retrieval Research, 2018, 8(3): 33-45.

基金资助

国家自然科学基金资助项目(62266027)

国家自然科学基金资助项目(U21B2027)

国家自然科学基金资助项目(U23A20388)

云南省科技重大专项资助项目(202302AD080003)

云南省科技重大专项资助项目(202303AP140008)

云南省基础研究重大专项资助项目(202401BC070021)

昆明理工大学“双一流”创建联合专项资助项目(202201BE070001-021)