Abstract
Dense Retriever (DR) for Open-domain textual question answering (OpenQA), which aims to retrieve passages from large data sources like Wikipedia or Google, has gained wide attention in recent years. Although DR models continuously refresh state-of-the-art performances, their improvement relies on negative sampling during the training process. Existing sampling strategies mainly focus on developing a complex algorithm based on computer science, and ignore the abundant semantic features of datasets. We discover that there exists obvious changes in semantic similarity and present a three-level hierarchy of semantic similarity: same topic, same class, other class, whose rationality is further demonstrated by ablation study. Based on this, we propose a hard negative sampling strategy named Hierarchical Semantic Similarity (HSS). Our HSS model performs negative sampling at semantic levels of topic and class, and experimental results on four datasets show that it achieves comparable or better retrieval performance compared with existing competitive baselines. The code is available in https://github.com/redirecttttt/HSS.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
When acquiring semantic information of a question, we extract topics and cluster its positive. Because most questions are no more than 10 words, with limited information.
References
Baudiš, P., Šedivý, J.: Modeling of the question answering task in the YodaQA system. In: Mothe, J., et al. (eds.) CLEF 2015. LNCS, vol. 9283, pp. 222–228. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24027-5_20
Berant, J., Chou, A., Frostig, R., Liang, P.: Semantic parsing on freebase from question-answer pairs. In: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pp. 1533–1544 (2013)
Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent dirichlet allocation. J. Mach. Learn. Res. 3(Jan), 993–1022 (2003)
Dolan, W., Quirk, C., Brockett, C., Dolan, B.: Unsupervised construction of large paraphrase corpora: exploiting massively parallel news sources (2004)
Gillick, D., et al.: Learning dense representations for entity retrieval. In: Proceedings of the 23rd Conference on Computational Natural Language Learning, pp. 528–537 (2019)
Hofstätter, S., Lin, S.C., Yang, J.H., Lin, J., Hanbury, A.: Efficiently teaching an effective dense retriever with balanced topic aware sampling. In: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 113–122 (2021)
Johnson, J., Douze, M., Jégou, H.: Billion-scale similarity search with GPUs. IEEE Trans. Big Data 7(3), 535–547 (2019)
Joshi, M., Choi, E., Weld, D.S., Zettlemoyer, L.: Triviaqa: a large scale distantly supervised challenge dataset for reading comprehension. In: Proceedings of the 55th Meeting of the Association for Computational Linguistics, pp. 1601–1611 (2017)
Karpukhin, V., et al.: Dense passage retrieval for open-domain question answering. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, pp. 6769–6781 (2020)
Kulis, B., et al.: Metric learning: a survey. Found. Trends® Mach. Learn. 5(4), 287–364 (2013)
Kwiatkowski, T., et al.: Natural questions: a benchmark for question answering research. Trans. Assoc. Comput. Linguist. 7, 453–466 (2019)
Lee, K., Chang, M.W., Toutanova, K.: Latent retrieval for weakly supervised open domain question answering. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 6086–6096 (2019)
Li, H., Xu, J., et al.: Semantic matching in search. Found. Trends® Inf. Retrieval 7(5), 343–469 (2014)
Liu, Y., Hashimoto, K., Zhou, Y., Yavuz, S., Xiong, C., Philip, S.Y.: Dense hierarchical retrieval for open-domain question answering. In: Findings of the Association for Computational Linguistics: EMNLP 2021, pp. 188–200 (2021)
Marelli, M., Menini, S., Baroni, M., Bentivogli, L., Bernardi, R., Zamparelli, R.: A sick cure for the evaluation of compositional distributional semantic models. In: Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC 2014), pp. 216–223 (2014)
Ren, R., et al.: A thorough examination on zero-shot dense retrieval. arXiv preprint arXiv:2204.12755 (2022)
Sciavolino, C., Zhong, Z., Lee, J., Chen, D.: Simple entity-centric questions challenge dense retrievers. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 6138–6148 (2021)
Xuan, H., Stylianou, A., Liu, X., Pless, R.: Hard negative examples are hard, but useful. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 126–142. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58568-6_8
Yih, W.T., Toutanova, K., Platt, J.C., Meek, C.: Learning discriminative projections for text similarity measures. In: Proceedings of the 15th Conference on Computational Natural Language Learning, pp. 247–256 (2011)
Zhan, J., Mao, J., Liu, Y., Guo, J., Zhang, M., Ma, S.: Optimizing dense retrieval model training with hard negatives. In: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 1503–1512 (2021)
Zhang, D., et al.: Supporting clustering with contrastive learning. In: NAACL-HLT (2021)
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
Xie, X., Liu, F., Gai, S., Huang, Z., Hu, M., Wang, A. (2023). HSS: A Hierarchical Semantic Similarity Hard Negative Sampling Method for Dense Retrievers. In: Dang-Nguyen, DT., et al. MultiMedia Modeling. MMM 2023. Lecture Notes in Computer Science, vol 13834. Springer, Cham. https://doi.org/10.1007/978-3-031-27818-1_25
Download citation
DOI: https://doi.org/10.1007/978-3-031-27818-1_25
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-27817-4
Online ISBN: 978-3-031-27818-1
eBook Packages: Computer ScienceComputer Science (R0)