[Purpose/Significance] To address the issues of over-reliance on the original retrieved document collection in pseudo-relevance feedback and the neglect of potential expansion elements in relevant documents by generation-augmented retrieval model in retrieval systems, this paper proposes a query expansion model based on generative model and pseudo-relevance feedback. [Method/Process] According to the advantages of both generative models and pseudo relevance feedback, it generated candidate extended word sets using query generative models and pseudo-relevance feedback, respectively. Then, it combined the two sets to obtain the final extended word set, achieving query expansion. Finally, taking NQ and TriviaQA as experimental data, it confirmed the efficiency of the proposed query expansion model using dense passage?retrieval. [Result/Conclusion] The experimental results demonstrates that the Top-k retrieval accuracy and EM of the proposed model is higher than the baseline ones. In addition, the effects of the number of pseudo-relevance feedback query words, the context category of the generative model, and the question category on the model performance are tested, and the experimental results verify the effectiveness of the proposed method. The proposed model can improve the quality of query expansion words and information retrieval performance.
[1] LI S, GONG C, ZHU Y, et al. Context-aware multi-level question embedding fusion for visual question answering[J]. Information fusion, 2024, 102: 102000.
[2] ZHU W, ZHANG X, YE L, et al. Query context expansion for open-domain question answering[J]. ACM transactions on Asian and low-resource language information processing, 2023, 22(8): 1-21.
[3] WANG J, PAN M, HE T, et al. A pseudo-relevance feedback framework combining relevance matching and semantic matching for information retrieval[J]. Information processing & management, 2020, 57(6): 102342.
[4] LEWIS M, LIU Y, GOYAL N, et al. BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension[C]//Proceedings of the 58th annual meeting of the Association for Computational Linguistics. Stroudsburg: Association for Computational Linguistics, 2020: 7871-7880.
[5] YU S, LIU J, YANG J, et al. Few-shot generative conversational query rewriting[C]//Proceedings of the 43rd international ACM SIGIR conference on research and development in information retrieval. New York: Association for Computing Machinery, 2020: 1933-1936.
[6] LIN S, YANG J, NOGUEIRA R F, et al. Query reformulation using query history for passage retrieval in conversational search[EB/OL]. [2024-04-05]. https://arxiv.org/pdf/2005.02230v1.pdf.
[7] MAO Y, HE P, LIU X, et al. Generation-augmented retrieval for open-domain question answering[C]//Proceedings of the 59th annual meeting of the Association for Computational Linguistics and the 11th international joint conference on natural language processing. Stroudsburg: Association for Computational Linguistics, 2021: 4089-4100.
[8] LV Y, ZHAI C. A comparative study of methods for estimating query language models with pseudo feedback[C]//Proceedings of the 18th ACM conference on information and knowledge management. New York: Association for Computing Machinery, 2009: 1895-1898.
[9] ROCCHIO J J. Relevance feedback in information retrieval[M]//SALTON G. The smart retrieval system-experiments in automatic document processing. Englewood Cliffs: Prentice-Hall, 1971: 313-323.
[10] PAN M, PEI Q L, LIU Y, et al. SPRF: a semantic pseudo-relevance feedback enhancement for information retrieval via ConceptNet[J]. Knowledge-based systems, 2023, 274: 110602.
[11] PAN M, HUANG J X, HE T, et al. A simple kernel co-occurrence-based enhancement for pseudo-relevance feedback[J]. Journal of Association for Information Science and Technology, 2020, 71(3): 264-281.
[12] LV Y, ZHAI C X. Positional relevance model for pseudo-relevance feedback[C]// Proceedings of the 33rd international ACM SIGIR conference on research and development in information retrieval. New York: Association for Computing Machinery, 2010: 579-586.
[13] AKLOUCHE B, BOUNHAS I, LIMANI Y. A discriminative method for global query expansion and term reweighting using co-occurrence graphs[J]. Journal of information science, 2023, 49(1): 183-206.
[14] NASREEN A J, JAMES A, W B C, et al. Umass at TREC 2004: novelty and HARD [C]//Proceedings of the thirteenth text retrieval conference. Amherst: University of Massachusetts Press, 2004: 189.
[15] ROY D, GANGULY D, MITRA M, et al. Word vector compositionality based relevance feedback using kernel density estimation[C]//Proceedings of the 25th ACM international on conference on information and knowledge management. New York: Association for Computing Machinery, 2016: 1281-1290.
[16] ZAMANI H, BRUCE CROFT W. Embedding-based query language models [C]//Proceedings of the 2016 ACM international conference on the theory of information retrieval. New York: Association for Computing Machinery, 2016: 147-156.
[17] 余传明, 蔡林, 胡莎莎, 等. 基于深度学习的查询扩展研究[J]. 情报学报, 2019, 38(10): 1066-1077. (YU C M, CAI L, HU S S, et al. Research on query expansion based on deep learning[J]. Journal of the China Society for Scientific and Technical Information, 2019, 38(10): 1066-1077.)
[18] 刘高军, 方晓, 段建勇.基于深度语义信息的查询扩展[J]. 计算机应用, 2020, 40(11): 3192-3197. (LIU G J, FANG X, DUAN J Y. Query extension based on deep semantic information[J]. Journal of computer applications, 2020, 40(11): 3192-3197.)
[19] CHUANG Y, FANG W, LI S, et al. Expand, rerank, and retrieve: query reranking for open-domain question answering[C]//Findings of the Association for Computational Linguistics: ACL 2023. Stroudsburg: Association for Computational Linguistics, 2023: 12131-12147.
[20] SINGH P, BHOWMICK P K. Semantics-aware query expansion using pseudo-relevance feedback[EB/OL]. [2024-04-05]. https://doi.org/10.1177/01655515231184831.
[21] VLADIMIR K, BARLAS O, SEWON M, et al. Dense passage retrieval for open-domain question answering[C]//Proceedings of the 2020 conference on empirical methods in natural language processing. Stroudsburg: Association for Computational Linguistics, 2020: 6769-6781.
[22] CLAVEAU V. Query expansion with artificially generated texts[EB/OL]. [2024-04-05]. https: //arxiv.org/abs/2012.08787.
[23] LEE M, GAO B, ZHANG R. Rare query expansion through generative adversarial networks in search advertising[C]//Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining. New York: Association for Computing Machinery, 2018: 500508.
[24] HUANG M, WANG D, LIU S, et al. GQE-PRF: generative query expansion with pseudo-relevance feedback[EB/OL]. [2024-04-05]. https://arxiv.org/abs/2108.06010.
[25] CHEN H, DOU Z, ZHU Y, et al. 2022. Enhancing user behavior sequence modeling by generative tasks for session search[C]//Proceedings of the 31st ACM international conference on information and knowledge management. New York: Association for Computing Machinery, 2022: 180-190.
[26] 潘敏. 基于潜在语义关系的伪相关反馈查询扩展技术研究[D]. 武汉: 华中师范大学, 2019. (PAN M. Research on pseudo relevance feedback query expansion technology based on latent semantic relation[D]. Wuhan: Central China Normal University, 2019.)
[27] TOM K, JENNIMARIA P, OLIVIA R, et al. Natural questions: a benchmark for question answering research[J]. Transactions of the Association for Computational Linguistics, 2019, 7: 452-466.
[28] MANDAR J, EUNSOL C, DANIEL W, et al. TriviaQA: a large scale distantly supervised challenge dataset for reading comprehension[C]//Proceedings of the 55th annual meeting of the Association for Computational Linguistics. Stroudsburg: Association for Computational Linguistics, 2017: 1601-1611.
[29] ROBERTSON S, ZARAGOZA H. The probabilistic relevance framework: BM25 and beyond[J]. Foundations & trends in information retrieval, 2009, 3(4): 333-389.
[30] LIN J, MA X, LIN S, et al. Pyserini: a python toolkit for reproducible information retrieval research with sparse and dense representations[C]//Proceedings of the 44th international ACM SIGIR conference on research and development in information retrieval. New York: Association for Computing Machinery, 2021: 2356-2362.
[31] DEVLIN J, CHANG M, 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. Stroudsburg: Association for Computational Linguistics, 2019: 4171-4186.
