Abstract
In information retrieval (IR) systems, trends and users’ interests may change over time, altering either the distribution of requests or contents to be recommended. Since neural ranking approaches heavily depend on the training data, it is crucial to understand the transfer capacity of recent IR approaches to address new domains in the long term. In this paper, we first propose a dataset based upon the MSMarco corpus aiming at modeling a long stream of topics as well as IR property-driven controlled settings. We then in-depth analyze the ability of recent neural IR models while continually learning those streams. Our empirical study highlights in which particular cases catastrophic forgetting occurs (e.g., level of similarity between tasks, peculiarities on text length, and ways of learning models) to provide future directions in terms of model design.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
- 2.
Using bert-base-uncased pretrain.
- 3.
- 4.
- 5.
Implemented in pyserini: https://github.com/castorini/pyserini.
- 6.
- 7.
If not the case, we sample one document to build the query-relevant document pairs.
References
Albakour, M.D., Macdonald, C., Ounis, I.: On sparsity and drift for effective real-time filtering in microblogs. In: Proceedings of the 22nd ACM International Conference on Information and Knowledge Management, CIKM 2013, p. 419–428. Association for Computing Machinery, New York (2013). https://doi.org/10.1145/2505515.2505709
Asghar, N., Mou, L., Selby, K.A., Pantasdo, K.D., Poupart, P., Jiang, X.: Progressive memory banks for incremental domain adaptation. In: ICLR arXiv:1811.00239 (2020)
Cai, F., Liang, S., de Rijke, M.: Time-sensitive personalized query auto-completion. In: Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management, CIKM 2014, pp. 1599–1608. Association for Computing Machinery, New York (2014). https://doi.org/10.1145/2661829.2661921
Cai, H., Chen, H., Zhang, C., Song, Y., Zhao, X., Yin, D.: Adaptive parameterization for neural dialogue generation. In: EMNLP-IJCNLP, pp. 1793–1802 (2019)
Dai, Z., Xiong, C., Callan, J., Liu, Z.: Convolutional neural networks for soft-matching n-grams in ad-hoc search. In: WSDM, pp. 126–134 (2018)
Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL-HLT, pp. 4171–4186 (2019)
Formal, T., Piwowarski, B., Clinchant, S.: SPLADE: sparse lexical and expansion model for first stage ranking. In: Diaz, F., Shah, C., Suel, T., Castells, P., Jones, R., Sakai, T. (eds.) SIGIR 2021: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, Virtual Event, Canada, 11–15 July 2021, pp. 2288–2292. ACM (2021). https://doi.org/10.1145/3404835.3463098
Gao, J., Xiong, C., Bennett, P.: Recent advances in conversational information retrieval. In: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2020, pp. 2421–2424. Association for Computing Machinery, New York (2020). https://doi.org/10.1145/3397271.3401418
Garcia, X., Constant, N., Parikh, A.P., Firat, O.: Towards continual learning for multilingual machine translation via vocabulary substitution. In: NAACL-HLT, pp. 1184–1192 (2021)
Guo, J., Fan, Y., Ai, Q., Croft, W.B.: A deep relevance matching model for ad-hoc retrieval. In: CIKM, pp. 55–64 (2016)
Hofstätter, S., Lin, S., Yang, J., Lin, J., Hanbury, A.: Efficiently teaching an effective dense retriever with balanced topic aware sampling. In: Diaz, F., Shah, C., Suel, T., Castells, P., Jones, R., Sakai, T. (eds.) SIGIR 2021: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, Virtual Event, Canada, pp. 113–122. ACM (2021)
Hui, K., Yates, A., Berberich, K., de Melo, G.: PACRR: a position-aware neural IR model for relevance matching. In: EMNLP, pp. 1049–1058 (2017)
Hui, K., Yates, A., Berberich, K., de Melo, G.: CO-PACRR: a context-aware neural IR model for ad-hoc retrieval. In: WSDM, pp. 279–287 (2018)
Karpukhin, V., et al.: Dense passage retrieval for open-domain question answering. In: Webber, B., Cohn, T., He, Y., Liu, Y. (eds.) Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, EMNLP 2020, Online, 16–20 November 2020, pp. 6769–6781. Association for Computational Linguistics (2020). https://doi.org/10.18653/v1/2020.emnlp-main.550
Khattab, O., Zaharia, M.: ColBERT: efficient and effective passage search via contextualized late interaction over BERT. In: SIGIR, pp. 39–48. ACM (2020)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Bengio, Y., LeCun, Y. (eds.) ICLR 2015 (2015)
Kirkpatrick, J., et al.: Overcoming catastrophic forgetting in neural networks. CoRR arXiv:1612.00796 (2016)
Lange, M.D., et al.: Continual learning: a comparative study on how to defy forgetting in classification tasks. CoRR arXiv:1909.08383 (2019)
Lee, S.: Toward continual learning for conversational agents. CoRR arXiv:1712.09943 (2017)
Li, X., Zhou, Y., Wu, T., Socher, R., Xiong, C.: Learn to grow: a continual structure learning framework for overcoming catastrophic forgetting. In: ICML, vol. 97, pp. 3925–3934 (2019)
Li, Z., Hoiem, D.: Learning without forgetting. IEEE Trans. Pattern Anal. Mach. Intell. 12, 2935–2947 (2018)
Lovón-Melgarejo, J., Soulier, L., Pinel-Sauvagnat, K., Tamine, L.: Studying catastrophic forgetting in neural ranking models. In: Hiemstra, D., Moens, M.-F., Mothe, J., Perego, R., Potthast, M., Sebastiani, F. (eds.) ECIR 2021. LNCS, vol. 12656, pp. 375–390. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-72113-8_25
Ma, X., dos Santos, C.N., Arnold, A.O.: Contrastive fine-tuning improves robustness for neural rankers. In: Zong, C., Xia, F., Li, W., Navigli, R. (eds.) Findings of the Association for Computational Linguistics: ACL/IJCNLP 2021, Findings of ACL, pp. 570–582, Online Event, 1–6 August 2021. Association for Computational Linguistics (2021). https://doi.org/10.18653/v1/2021.findings-acl.51
MacAvaney, S., Yates, A., Cohan, A., Goharian, N.: CEDR: contextualized embeddings for document ranking. In: SIGIR, pp. 1101–1104 (2019)
de Masson d’Autume, C., Ruder, S., Kong, L., Yogatama, D.: Episodic memory in lifelong language learning. CoRR arXiv:1906.01076 (2019)
McCreadie, R., et al.: University of Glasgow at TREC 2014: experiments with terrier in contextual suggestion, temporal summarisation and web tracks. In: Voorhees, E.M., Ellis, A. (eds.) Proceedings of The Twenty-Third Text REtrieval Conference, TREC 2014, Gaithersburg, Maryland, USA, vol. 500–308, 19–21 November 2014. National Institute of Standards and Technology (NIST), NIST Special Publication (2014). http://trec.nist.gov/pubs/trec23/papers/pro-uogTr_cs-ts-web.pdf
McDonald, R.T., Brokos, G., Androutsopoulos, I.: Deep relevance ranking using enhanced document-query interactions. In: EMNLP, pp. 1849–1860 (2018)
Mitra, B., Craswell, N.: An introduction to neural information retrieval. Found. Trends Inf. Retr. 13(1), 1–126 (2018). https://doi.org/10.1561/1500000061
Nguyen, T., et al.: MS MARCO: a human generated machine reading comprehension dataset. In: Besold, T.R., Bordes, A., d’Avila Garcez, A.S., Wayne, G. (eds.) Proceedings of the Workshop on Cognitive Computation: Integrating Neural and Symbolic Approaches 2016 Co-located with the 30th Annual Conference on Neural Information Processing Systems (NIPS 2016), Barcelona, Spain, December 9, 2016, CEUR Workshop Proceedings, vol. 1773. CEUR-WS.org (2016). http://ceur-ws.org/Vol-1773/CoCoNIPS_2016_paper9.pdf
Nishida, K., Saito, I., Otsuka, A., Asano, H., Tomita, J.: Retrieve-and-read: multi-task learning of information retrieval and reading comprehension. In: Proceedings of the 27th ACM International Conference on Information and Knowledge Management, CIKM 2018, pp. 647–656. Association for Computing Machinery, New York (2018). https://doi.org/10.1145/3269206.3271702
Nogueira, R., Jiang, Z., Pradeep, R., Lin, J.: Document ranking with a pretrained sequence-to-sequence model. In: EMNLP, pp. 708–718 (2020)
Onal, K.D., et al.: Neural information retrieval: at the end of the early years. Inf. Retr. J. 21(2–3), 111–182 (2018). https://doi.org/10.1007/s10791-017-9321-y
Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345–1359 (2010)
Rebuffi, S., Kolesnikov, A., Sperl, G., Lampert, C.H.: iCaRL: incremental classifier and representation learning. In: CVPR, pp. 5533–5542 (2017)
Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using Siamese BERT-networks. In: EMNLP (2019). http://arxiv.org/abs/1908.10084
Robertson, S.E., Walker, S., Hancock-Beaulieu, M., Gull, A., Lau, M.: Okapi at TREC. In: TREC, vol. 500–207, pp. 21–30 (1992)
Sankepally, R.: Event information retrieval from text. In: Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2019, p. 1447. Association for Computing Machinery, New York (2019). https://doi.org/10.1145/3331184.3331415
Sun, F., Ho, C., Lee, H.: LAMOL: language modeling for lifelong language learning. In: ICLR (2020)
Vaswani, A., et al.: Attention is all you need. In: NeurIPS, pp. 5998–6008 (2017)
Veniat, T., Denoyer, L., Ranzato, M.: Efficient continual learning with modular networks and task-driven priors. CoRR arXiv:2012.12631 (2020)
Wiese, G., Weissenborn, D., Neves, M.: Neural domain adaptation for biomedical question answering. In: CoNLL 2017, pp. 281–289 (2017)
Xiong, C., Dai, Z., Callan, J., Liu, Z., Power, R.: End-to-end neural ad-hoc ranking with kernel pooling. In: SIGIR, pp. 55–64 (2017)
Yang, W., Xie, Y., Tan, L., Xiong, K., Li, M., Lin, J.: Data augmentation for BERT fine-tuning in open-domain question answering. CoRR arXiv:1904.06652 (2019)
Zhao, T., Lu, X., Lee, K.: SPARTA: efficient open-domain question answering via sparse transformer matching retrieval. In: Toutanova, K., et al. (eds.) Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2021, Online, 6–11 June 2021, pp. 565–575. Association for Computational Linguistics (2021). https://doi.org/10.18653/v1/2021.naacl-main.47
Acknowledgements
We thank the ANR JCJC SESAMS project (ANR-18-CE23-0001) for supporting this work. This work was performed using HPC resources from GENCI-IDRIS (Grant 2021-101681).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Gerald, T., Soulier, L. (2022). Continual Learning of Long Topic Sequences in Neural Information Retrieval. In: Hagen, M., et al. Advances in Information Retrieval. ECIR 2022. Lecture Notes in Computer Science, vol 13185. Springer, Cham. https://doi.org/10.1007/978-3-030-99736-6_17
Download citation
DOI: https://doi.org/10.1007/978-3-030-99736-6_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-99735-9
Online ISBN: 978-3-030-99736-6
eBook Packages: Computer ScienceComputer Science (R0)