Skip to main content

Advertisement

Springer Nature Link
Log in

Mutually improved dense retriever and GNN-based reader for arbitrary-hop open-domain question answering

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Open-domain question answering (OpenQA) requires not only a high-precision reader, but also high-quality retrieval of related passages. Particularly, real-world OpenQA usually involves multi-hop retrieval and reading to deal with complex questions that need bridging information. In this paper, we investigate the mutual promotion of dense retrievers and Graph Neural Network-based readers to improve OpenQA. Specifically, we introduce an alternate training strategy where the scores of the dense retriever and the GNN-based reader are used as correction weights to enhance the performance of each other. We leverage off-the-shelf strong dense retrievers such as Dense Passage Retriever (DPR) and Multi-hop Dense Retriever for retrieval. For the reader, we extend the Asynchronous Multi-grained Graph Network (AMGN) by defining passage nodes and passage-level relationships to cater to the retrieval. It is worth mentioning that through the Recurrent Neural Networks based question reformulation mechanism in AMGN and appropriate preprocessing, the proposed training strategy can be free from the constraints of fixed-hop question answering. We evaluate the proposed framework on several prevalent OpenQA datasets, Natural Questions, TriviaQA, and HotpotQA, achieving competitive results compared with other published models. Extensive experimental analyses illustrate the effectiveness of enhanced passage-aware AMGN and mutual promotion.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
€32.70 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price includes VAT (France)

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Notes

  1. The gold sequence contains the gold passage of each hop. If there are multiple gold sequences, we treat them as different training samples.

  2. https://github.com/huggingface/transformers

  3. https://github.com/facebookresearch/DPR

  4. https://github.com/facebookresearch/multihop_dense_retrieval

  5. https://github.com/woshiyyya/DFGN-pytorch

  6. https://hotpotqa.github.io/

References

  1. Asai A, Hashimoto K, Hajishirzi H, Socher R, Xiong C (2020) Learning to retrieve reasoning paths over wikipedia graph for question answering. In: 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. OpenReview.net. https://openreview.net/forum?id=SJgVHkrYDH

  2. Beltagy I, Peters ME, Cohan A (2020) Longformer: The long-document transformer. CoRR http://arxiv.org/abs/2004.05150

  3. Cao ND, Aziz W, Titov I (2019) Question answering by reasoning across documents with graph convolutional networks. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, USA, June 2-7, 2019, Volume 1 (Long and Short Papers), pp. 2306–2317. Association for Computational Linguistics. https://doi.org/10.18653/v1/n19-1240

  4. Chen D, Fisch A, Weston J, Bordes A (2017) Reading wikipedia to answer open-domain questions. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, Vancouver, Canada, July 30 - August 4, Volume 1: Long Papers, pp. 1870–1879. Association for Computational Linguistics (2017). https://doi.org/10.18653/v1/P17-1171

  5. Das R, Dhuliawala S, Zaheer M, McCallum A (2019) Multi-step retriever-reader interaction for scalable open-domain question answering. In: 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019. OpenReview.net. https://openreview.net/forum?id=HkfPSh05K7

  6. Devlin J, Chang M, Lee K, Toutanova K (2019) BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, USA, June 2-7, 2019, Volume 1 (Long and Short Papers), pp. 4171–4186. Association for Computational Linguistics. https://doi.org/10.18653/v1/n19-1423

  7. Dhingra B, Jin Q, Yang Z, Cohen WW, Salakhutdinov R (2018) Neural models for reasoning over multiple mentions using coreference. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT, New Orleans, Louisiana, USA, June 1-6, 2018, Volume 2 (Short Papers), pp. 42–48. Association for Computational Linguistics. https://doi.org/10.18653/v1/n18-2007

  8. Ding M, Zhou C, Chen Q, Yang H, Tang J (2019) Cognitive graph for multi-hop reading comprehension at scale. In: Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL 2019, Florence, Italy, July 28- August 2, 2019, Volume 1: Long Papers, pp. 2694–2703. Association for Computational Linguistics. https://doi.org/10.18653/v1/p19-1259

  9. Fang Y, Sun S, Gan Z, Pillai R, Wang S, Liu J (2020) Hierarchical graph network for multi-hop question answering. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, EMNLP 2020, Online, November 16-20, 2020, pp. 8823–8838. Association for Computational Linguistics. https://doi.org/10.18653/v1/2020.emnlp-main.710

  10. Feldman Y, El-Yaniv R (2019) Multi-hop paragraph retrieval for open-domain question answering. In: Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL 2019, Florence, Italy, July 28- August 2, 2019, Volume 1: Long Papers, pp. 2296–2309. Association for Computational Linguistics. https://doi.org/10.18653/v1/p19-1222

  11. Gao L, Callan J (2021) Condenser: a pre-training architecture for dense retrieval. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021, Virtual Event / Punta Cana, Dominican Republic, 7-11 November, 2021, pp. 981–993. Association for Computational Linguistics. https://aclanthology.org/2021.emnlp-main.75

  12. Gao L, Callan J (2021) Unsupervised corpus aware language model pre-training for dense passage retrieval. CoRR abs/2108.05540 (2021). http://arxiv.org/abs/2108.05540

  13. Glass MR, Gliozzo A, Chakravarti R, Ferritto A, Pan L, Bhargav GPS, Garg D, Sil A (2020) Span selection pre-training for question answering. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020, Online, July 5-10, 2020, pp. 2773–2782. Association for Computational Linguistics. https://doi.org/10.18653/v1/2020.acl-main.247

  14. Guu K, Lee K, Tung Z, Pasupat P, Chang M (2020) Retrieval augmented language model pre-training. In: Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13-18 July 2020, Virtual Event, Proceedings of Machine Learning Research, vol. 119, pp. 3929–3938. PMLR. http://proceedings.mlr.press/v119/guu20a.html

  15. Hu M, Peng Y, Huang Z, Qiu X, Wei F, Zhou M (2018) Reinforced mnemonic reader for machine reading comprehension. In: Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI 2018, July 13-19, 2018, Stockholm, Sweden, pp. 4099–4106. ijcai.org. https://doi.org/10.24963/ijcai.2018/570

  16. Huang H, Zhu C, Shen Y, Chen W (2018) Fusionnet: Fusing via fully-aware attention with application to machine comprehension. In: 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings. OpenReview.net. https://openreview.net/forum?id=BJIgi_eCZ

  17. Izacard G, Grave E (2021) Distilling knowledge from reader to retriever for question answering. In: 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021. OpenReview.net. https://openreview.net/forum?id=NTEz-6wysdb

  18. Izacard G, Grave E (2021) Leveraging passage retrieval with generative models for open domain question answering. In: Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, EACL 2021, Online, April 19 - 23, 2021, pp. 874–880. Association for Computational Linguistics. https://www.aclweb.org/anthology/2021.eacl-main.74/

  19. Jiang Y, Bansal M (2019) Self-assembling modular networks for interpretable multi-hop reasoning. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019, Hong Kong, China, November 3-7, 2019, pp. 4473–4483. Association for Computational Linguistics. https://doi.org/10.18653/v1/D19-1455

  20. Jiang Y, Joshi N, Chen Y, Bansal M (2019) Explore, propose, and assemble: An interpretable model for multi-hop reading comprehension. In: Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL 2019, Florence, Italy, July 28- August 2, 2019, Volume 1: Long Papers, pp. 2714–2725. Association for Computational Linguistics. https://doi.org/10.18653/v1/p19-1261

  21. Johnson J, Douze M, Jégou H (2021) Billion-scale similarity search with gpus. IEEE Trans Big Data 7(3):535–547. https://doi.org/10.1109/TBDATA.2019.2921572

    Article  Google Scholar 

  22. Joshi M, Choi E, Weld DS, Zettlemoyer L (2017) Triviaqa: A large scale distantly supervised challenge dataset for reading comprehension. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017, Vancouver, Canada, July 30 - August 4, Volume 1: Long Papers, pp. 1601–1611. Association for Computational Linguistics. https://doi.org/10.18653/v1/P17-1147

  23. Karpukhin V, Oguz B, Min S, Lewis PSH, Wu L, Edunov S, Chen D, Yih W (2020) Dense passage retrieval for open-domain question answering. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, EMNLP 2020, Online, November 16-20, 2020, pp. 6769–6781. Association for Computational Linguistics. https://doi.org/10.18653/v1/2020.emnlp-main.550

  24. Khashabi D, Chaturvedi S, Roth M, Upadhyay S, Roth D (2018) Looking beyond the surface: A challenge set for reading comprehension over multiple sentences. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2018, New Orleans, Louisiana, USA, June 1-6, 2018, Volume 1 (Long Papers), pp. 252–262. Association for Computational Linguistics. https://doi.org/10.18653/v1/n18-1023

  25. Khattab O, Zaharia M (2020) 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, SIGIR 2020, Virtual Event, China, July 25-30, 2020, pp. 39–48. ACM. https://doi.org/10.1145/3397271.3401075

  26. Kociský T, Schwarz J, Blunsom P, Dyer C, Hermann KM, Melis G, Grefenstette E (2018) The narrativeqa reading comprehension challenge. Trans. Assoc. Comput. Linguistics 6, 317–328. https://transacl.org/ojs/index.php/tacl/article/view/1197

  27. Kwiatkowski T, Palomaki J, Redfield O, Collins M, Parikh AP, Alberti C, Epstein D, Polosukhin I, Devlin J, Lee K, Toutanova K, Jones L, Kelcey M, Chang M, Dai AM, Uszkoreit J, Le Q, Petrov S (2019) Natural questions: a benchmark for question answering research. Trans. Assoc. Comput. Linguistics 7, 452–466. https://transacl.org/ojs/index.php/tacl/article/view/1455

  28. Lai G, Xie Q, Liu H, Yang Y, Hovy EH (2017) RACE: large-scale reading comprehension dataset from examinations. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017, Copenhagen, Denmark, September 9-11, 2017, pp. 785–794. Association for Computational Linguistics. https://doi.org/10.18653/v1/d17-1082

  29. Lan Z, Chen M, Goodman S, Gimpel K, Sharma P, Soricut R (2020) ALBERT: A lite BERT for self-supervised learning of language representations. In: 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. OpenReview.net. https://openreview.net/forum?id=H1eA7AEtvS

  30. Lee K, Chang M, Toutanova K (2019) Latent retrieval for weakly supervised open domain question answering. In: Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL 2019, Florence, Italy, July 28- August 2, 2019, Volume 1: Long Papers, pp. 6086–6096. Association for Computational Linguistics. https://doi.org/10.18653/v1/p19-1612

  31. Lewis PSH, Perez E, Piktus A, Petroni F, Karpukhin V, Goyal N, Küttler H, Lewis M, Yih W, Rocktäschel T, Riedel S, Kiela D (2020) Retrieval-augmented generation for knowledge-intensive NLP tasks. In: Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual. https://proceedings.neurips.cc/paper/2020/hash/6b493230205f780e1bc26945df7481e5-Abstract.html

  32. Li R, Wang L, Wang S, Jiang Z (2021) Asynchronous multi-grained graph network for interpretable multi-hop reading comprehension. In: Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI 2021, Virtual Event / Montreal, Canada, 19-27 August 2021, pp. 3857–3863. ijcai.org. https://doi.org/10.24963/ijcai.2021/531

  33. Li S, Li X, Shang L, Jiang X, Liu Q, Sun C, Ji Z, Liu B (2021) Hopretriever: Retrieve hops over wikipedia to answer complex questions. In: Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, EAAI 2021, Virtual Event, February 2-9, 2021, pp. 13279–13287. AAAI Press. https://ojs.aaai.org/index.php/AAAI/article/view/17568

  34. Liu Y, Ott M, Goyal N, Du J, Joshi M, Chen D, Levy O, Lewis M, Zettlemoyer L, Stoyanov V (2019) Roberta: A robustly optimized BERT pretraining approach. CoRR abs/1907.11692. http://arxiv.org/abs/1907.11692

  35. Luan Y, Eisenstein J, Toutanova K, Collins M (2021) Sparse, dense, and attentional representations for text retrieval. Trans. Assoc. Comput. Linguistics 9, 329–345. https://transacl.org/ojs/index.php/tacl/article/view/2383

  36. Mao Y, He P, Liu X, Shen Y, Gao J, Han J, Chen W (2021) Generation-augmented retrieval for open-domain question answering. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL/IJCNLP 2021, (Volume 1: Long Papers), Virtual Event, August 1-6, 2021, pp. 4089–4100. Association for Computational Linguistics. https://doi.org/10.18653/v1/2021.acl-long.316

  37. Min S, Zhong V, Zettlemoyer L, Hajishirzi (2019) Multi-hop reading comprehension through question decomposition and rescoring. In: Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL 2019, Florence, Italy, July 28- August 2, 2019, Volume 1: Long Papers, pp. 6097–6109. Association for Computational Linguistics. https://doi.org/10.18653/v1/p19-1613

  38. Nguyen T, Rosenberg M, Song X, Gao J, Tiwary S, Majumder R, Deng L (2016) MS MARCO: A human generated machine reading comprehension dataset. In: 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. http://ceur-ws.org/Vol-1773/CoCoNIPS_2016_paper9.pdf

  39. Nie Y, Wang S, Bansal M (2019) Revealing the importance of semantic retrieval for machine reading at scale. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019, Hong Kong, China, November 3-7, 2019, pp. 2553–2566. Association for Computational Linguistics. https://doi.org/10.18653/v1/D19-1258

  40. Nishida K, Nishida K, Nagata M, Otsuka A, Saito I, Asano H, Tomita J (2019) Answering while summarizing: Multi-task learning for multi-hop QA with evidence extraction. In: Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL 2019, Florence, Italy, July 28- August 2, 2019, Volume 1: Long Papers, pp. 2335–2345. Association for Computational Linguistics. https://doi.org/10.18653/v1/p19-1225

  41. Perez E, Lewis PSH, Yih W, Cho K, Kiela D (2020) Unsupervised question decomposition for question answering. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, EMNLP 2020, Online, November 16-20, 2020, pp. 8864–8880. Association for Computational Linguistics. https://doi.org/10.18653/v1/2020.emnlp-main.713

  42. Qi P, Lee H, Sido OT, Manning CD (2020) Retrieve, rerank, read, then iterate: Answering open-domain questions of arbitrary complexity from text. CoRR http://arxiv.org/abs/2010.12527

  43. Qi P, Lin X, Mehr L, Wang Z, Manning CD (2019) Answering complex open-domain questions through iterative query generation. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019, Hong Kong, China, November 3-7, 2019, pp. 2590–2602. Association for Computational Linguistics. https://doi.org/10.18653/v1/D19-1261

  44. Qiu L, Xiao Y, Qu Y, Zhou H, Li L, Zhang W, Yu Y (2019) Dynamically fused graph network for multi-hop reasoning. In: Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL 2019, Florence, Italy, July 28- August 2, 2019, Volume 1: Long Papers, pp. 6140–6150. Association for Computational Linguistics. https://doi.org/10.18653/v1/p19-1617

  45. Qu Y, Ding Y, Liu J, Liu K, Ren R, Zhao WX, Dong D, Wu H, Wang H (2021) Rocketqa: An optimized training approach to dense passage retrieval for open-domain question answering. In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2021, Online, June 6-11, 2021, pp. 5835–5847. Association for Computational Linguistics. https://www.aclweb.org/anthology/2021.naacl-main.466/

  46. Rajpurkar P, Zhang J, Lopyrev K, Liang P (2016) Squad: 100, 000+ questions for machine comprehension of text. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, EMNLP 2016, Austin, Texas, USA, November 1-4, 2016, pp. 2383–2392. The Association for Computational Linguistics. https://doi.org/10.18653/v1/d16-1264

  47. Reddy S, Chen D, Manning CD (2019) Coqa: A conversational question answering challenge. Trans. Assoc. Comput. Linguistics 7, 249–266. https://transacl.org/ojs/index.php/tacl/article/view/1572

  48. Robertson SE, Zaragoza H (2009) The probabilistic relevance framework: BM25 and beyond. Found Trends Inf Retr 3(4):333–389. https://doi.org/10.1561/1500000019

    Article  Google Scholar 

  49. Sachan DS, Patwary M, Shoeybi M, Kant N, Ping W, Hamilton WL, Catanzaro B (2020) End-to-end training of neural retrievers for open-domain question answering. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL/IJCNLP 2021, (Volume 1: Long Papers), Virtual Event, August 1-6, 2021, pp. 6648–6662. Association for Computational Linguistics. https://aclanthology.org/2021.acl-long.519

  50. Sachan DS, Reddy S, Hamilton WL, Dyer C, Yogatama D (2021) End-to-end training of multi-document reader and retriever for open-domain question answering. CoRR . http://arxiv.org/abs/2106.05346

  51. Seo MJ, Kembhavi A, Farhadi A, Hajishirzi H (2017) Bidirectional attention flow for machine comprehension. In: 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings. OpenReview.net. https://openreview.net/forum?id=HJ0UKP9ge

  52. Shao N, Cui Y, Liu T, Wang S, Hu G (2020) Is graph structure necessary for multi-hop question answering? In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, EMNLP 2020, Online, November 16-20, 2020, pp. 7187–7192. Association for Computational Linguistics. https://doi.org/10.18653/v1/2020.emnlp-main.583

  53. Shao N, Cui Y, Liu T, Wang S, Hu G (2021) Memory augmented sequential paragraph retrieval for multi-hop question answering. CoRR . http://arxiv.org/abs/2102.03741

  54. Song L, Wang Z, Yu M, Zhang Y, Florian R, Gildea D (2018) Exploring graph-structured passage representation for multi-hop reading comprehension with graph neural networks. CoRR. http://arxiv.org/abs/1809.02040

  55. Tu M, Huang K, Wang G, Huang J, He X, Zhou B (2020) Select, answer and explain: Interpretable multi-hop reading comprehension over multiple documents. In: The Thirty-Fourth AAAI Conference on Artificial Intelligence, AAAI 2020, The Thirty-Second Innovative Applications of Artificial Intelligence Conference, IAAI 2020, The Tenth AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2020, New York, NY, USA, February 7-12, 2020, pp. 9073–9080. AAAI Press. https://aaai.org/ojs/index.php/AAAI/article/view/6441

  56. Tu M, Wang G, Huang J, Tang Y, He X, Zhou B (2019) Multi-hop reading comprehension across multiple documents by reasoning over heterogeneous graphs. In: Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL 2019, Florence, Italy, July 28- August 2, 2019, Volume 1: Long Papers, pp. 2704–2713. Association for Computational Linguistics. https://doi.org/10.18653/v1/p19-1260

  57. Wang W, Yang N, Wei F, Chang B, Zhou M (2017) Gated self-matching networks for reading comprehension and question answering. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017, Vancouver, Canada, July 30 - August 4, Volume 1: Long Papers, pp. 189–198. Association for Computational Linguistics. https://doi.org/10.18653/v1/P17-1018

  58. Welbl J, Stenetorp P, Riedel S (2018) Constructing datasets for multi-hop reading comprehension across documents. Trans. Assoc. Comput. Linguistics 6, 287–302. https://transacl.org/ojs/index.php/tacl/article/view/1325

  59. Xiong L, Xiong C, Li Y, Tang K, Liu J, Bennett PN, Ahmed J, Overwijk A (2021) Approximate nearest neighbor negative contrastive learning for dense text retrieval. In: 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021. OpenReview.net. https://openreview.net/forum?id=zeFrfgyZln

  60. Xiong W, Li XL, Iyer S, Du J, Lewis PSH, Wang WY, Mehdad Y, Yih S, Riedel S, Kiela D, Oguz B (2021) Answering complex open-domain questions with multi-hop dense retrieval. In: 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021. OpenReview.net. https://openreview.net/forum?id=EMHoBG0avc1

  61. Yadav V, Bethard S, Surdeanu M (2020) Unsupervised alignment-based iterative evidence retrieval for multi-hop question answering. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020, Online, July 5-10, 2020, pp. 4514–4525. Association for Computational Linguistics. https://doi.org/10.18653/v1/2020.acl-main.414

  62. Yang Z, Dai Z, Yang Y, Carbonell JG, Salakhutdinov R, Le QV (2019) Xlnet: Generalized autoregressive pretraining for language understanding. In: Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada, pp. 5754–5764. https://proceedings.neurips.cc/paper/2019/hash/dc6a7e655d7e5840e66733e9ee67cc69-Abstract.html

  63. Yang Z, Qi P, Zhang S, Bengio Y, Cohen WW, Salakhutdinov R, Manning CD (2018) Hotpotqa: A dataset for diverse, explainable multi-hop question answering. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium, October 31 - November 4, 2018, pp. 2369–2380. Association for Computational Linguistics. https://doi.org/10.18653/v1/d18-1259

  64. Yih W, Toutanova K, Platt JC, Meek C (2011) Learning discriminative projections for text similarity measures. In: Proceedings of the Fifteenth Conference on Computational Natural Language Learning, CoNLL 2011, Portland, Oregon, USA, June 23-24, 2011, pp. 247–256. ACL. https://www.aclweb.org/anthology/W11-0329/

  65. Zaheer M, Guruganesh G, Dubey KA, Ainslie J, Alberti C, Ontañón S, Pham P, Ravula A, Wang Q, Yang L, Ahmed A (2020) Big bird: Transformers for longer sequences. In: Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual. https://proceedings.neurips.cc/paper/2020/hash/c8512d142a2d849725f31a9a7a361ab9-Abstract.html

  66. Zhang Y, Nie P, Ramamurthy A, Song L (2021) Answering any-hop open-domain questions with iterative document reranking. In: SIGIR ’21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, Virtual Event, Canada, July 11-15, 2021, pp. 481–490. ACM. https://doi.org/10.1145/3404835.3462853

  67. Zhao C, Xiong C, Rosset C, Song X, Bennett PN, Tiwary S (2020) Transformer-xh: Multi-evidence reasoning with extra hop attention. In: 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. OpenReview.net. https://openreview.net/forum?id=r1eIiCNYwS

Download references

Author information

Authors and Affiliations

  1. School of Computer Science and Engineering, Northwestern Polytechnical University, 710072, Xi’an, People’s Republic of China

    Ronghan Li, Lifang Wang, Zejun Jiang, Zhongtian Hu, Meng Zhao & Xinyu Lu

Authors
  1. Ronghan Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Lifang Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zejun Jiang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Zhongtian Hu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Meng Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Xinyu Lu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Lifang Wang.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Li, R., Wang, L., Jiang, Z. et al. Mutually improved dense retriever and GNN-based reader for arbitrary-hop open-domain question answering. Neural Comput & Applic 34, 11831–11851 (2022). https://doi.org/10.1007/s00521-022-07072-0

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-022-07072-0

Keywords

Search

Navigation