CoChat
Sign Up
Cited by 351Topic ModelingInformation Retrieval and Search BehaviorNatural Language Processing Techniques

The DOI matches its Crossref record; 8 of the 8 references it cites were found in a registry or an index.

R3: Reinforced Ranker-Reader for Open-Domain Question Answering

Open access
Wang, Shuohang, Yu, Mo, Guo, Xiaoxiao, Wang, Zhiguo, Klinger, Tim, Zhang, Wei, Chang, Shiyu, Tesauro, Gerry, Zhou, Bowen, Jiang, Jing·2018·Proceedings of the AAAI Conference on Artificial Intelligence
DOI 10.1609/aaai.v32i1.12053
Open this paper in CoChat — free account

Abstract

In recent years researchers have achieved considerable success applying neural network methods to question answering (QA). These approaches have achieved state of the art results in simplified closed-domain settings such as the SQuAD (Rajpurkar et al. 2016) dataset, which provides a pre-selected passage, from which the answer to a given question may be extracted. More recently, researchers have begun to tackle open-domain QA, in which the model is given a question and access to a large corpus (e.g., wikipedia) instead of a pre-selected passage (Chen et al. 2017a). This setting is more complex as it requires large-scale search for relevant passages by an information retrieval component, combined with a reading comprehension model that “reads” the passages to generate an answer to the question. Performance in this setting lags well behind closed-domain performance. In this paper, we present a novel open-domain QA system called Reinforced Ranker-Reader (R3), based on two algorithmic innovations. First, we propose a new pipeline for open-domain QA with a Ranker component, which learns to rank retrieved passages in terms of likelihood of extracting the ground-truth answer to a given question. Second, we propose a novel method that jointly trains the Ranker along with an answer-extraction Reader model, based on reinforcement learning. We report extensive experimental results showing that our method significantly improves on the state of the art for multiple open-domain QA datasets.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1609/aaai.v32i1.12053

Cites

8 of 8 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Some work optimizes the retrieval module to aid in a specific, downstream task such as question answering, using search, reinforcement learning, or a latent variable approach as in our work.

    “Some work optimizes the retrieval module to aid in a specific, downstream task such as question answering, using search [46], reinforcement learning [6, 63, 62], or a latent variable approach [31, 20] as in our work.”

    From Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks (2020) · cites this paper as [63]

  • Some work optimizes the retrieval module to aid in a specific, downstream task such as question answering, using search, reinforcement learning, or a latent variable approach as in our work.

    “Some work optimizes the retrieval module to aid in a specific, downstream task such as question answering, using search [46], reinforcement learning [6, 63, 62], or a latent variable approach [31, 20] as in our work.”

    From Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks (2020) · cites this paper as [62]

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Flagged first, then by citations

Research works printed but not linked: 25

  1. Baudiš, P., and Šedivỳ, J. 2015. Modeling of the ques- tion answering task in the yodaqa system. In Intl. Conf. of the Cross-Language Evaluation Forum for European Lan- guages.
  2. Berant, J.; Chou, A.; Frostig, R.; and Liang, P. 2013. Se- mantic parsing on freebase from question-answer pairs. In Proc. of Conf. on EMNLP.
  3. Chen, T., and Van Durme, B. 2017. Discriminative informa- tion retrieval for question answering sentence selection. In Proc. of Conf. on EACL.
  4. Chen, Q.; Zhu, X.; Ling, Z.; Wei, S.; Jiang, H.; and Inkpen, D. 2017b. Enhanced lstm for natural language inference. In Proc. of ACL.
  5. Cheng, J., and Lapata, M. 2016. Neural summarization by extracting sentences and words. In Proc. of ACL.
  6. Choi, E.; Hewlett, D.; Uszkoreit, J.; Polosukhin, I.; Lacoste, A.; and Berant, J. 2017. Coarse-to-fine question answering for long documents. In Proc. of ACL.
  7. Dhingra, B.; Mazaitis, K.; and Cohen, W. W. 2017. QUASAR: Datasets for question answering by search and reading. arXiv preprint arXiv:1707.03904. · arXiv
  8. Dunn, M.; Sagun, L.; Higgins, M.; Guney, U.; Cirik, V.; and Cho, K. 2017. SearchQA: A new q&a dataset aug- mented with context from a search engine. arXiv preprint arXiv:1704.05179. · arXiv
  9. Ferrucci, D.; Brown, E.; Chu-Carroll, J.; Fan, J.; Gondek, D.; Kalyanpur, A. A.; et al. 2010. Building watson: An overview of the deepqa project. AI magazine 31(3):59-79.
  10. Green Jr, B. F.; Wolf, A. K.; Chomsky, C.; and Laughery, K. 1961. Baseball: an automatic question-answerer. In Papers presented at the May 9-11, 1961, western joint IRE-AIEE- ACM computer Conf., 219-224. ACM.
  11. Kwok, C.; Etzioni, O.; and Weld, D. S. 2001. Scaling ques- tion answering to the web. ACM Transactions on Informa- tion Systems (TOIS) 19(3):242-262.
  12. Mnih, V.; Heess, N.; Graves, A.; et al. 2014. Recurrent mod- els of visual attention. In Advances in NIPS, 2204-2212.
  13. Narasimhan, K.; Yala, A.; and Barzilay, R. 2016. Improving information extraction by acquiring external evidence with reinforcement learning. In Proc. of EMNLP.
  14. Nguyen, T.; Rosenberg, M.; Song, X.; Gao, J.; Tiwary, S.; Majumder, R.; and Deng, L. 2016. MS MARCO: A human generated machine reading comprehension dataset. arXiv preprint arXiv:1611.09268. · arXiv
  15. Pennington, J.; Socher, R.; and Manning, C. D. 2014. GloVe: Global vectors for word representation. In Proc. of Conf. on EMNLP.
  16. Seo, M.; Kembhavi, A.; Farhadi, A.; and Hajishirzi, H. 2017. Bidirectional attention flow for machine comprehension. In Proc. of ICLR.
  17. Voorhees, E. M., and Tice, D. M. 2000. Building a question answering test collection. In Proc. of 23rd annual Intl. ACM SIGIR Conf. on Research and development in information retrieval, 200-207. ACM.
  18. Wang, S., and Jiang, J. 2016. Learning natural language inference with LSTM. In Proc. of Conf. on NAACL.
  19. Wang, S., and Jiang, J. 2017a. A compare-aggregate model for matching text sequences. In Proc. of ICLR.
  20. Wang, S., and Jiang, J. 2017b. Machine comprehension using match-LSTM and answer pointer. In Proc. of ICLR.
  21. Wang, Z.; Mi, H.; Hamza, W.; and Florian, R. 2016. Multi- perspective context matching for machine comprehension. arXiv preprint arXiv:1612.04211. · arXiv
  22. Wang, W.; Yang, N.; Wei, F.; Chang, B.; and Zhou, M. 2017. Gated self-matching networks for reading comprehension and question answering. In Proc. of ACL.
  23. Wang, M.; Smith, N. A.; and Mitamura, T. 2007. What is the jeopardy model? a quasi-synchronous grammar for qa. In Proc. of Conf. on EMNLP.
  24. Xiong, C.; Zhong, V.; and Socher, R. 2017. Dynamic coat- tention networks for question answering. In Proc. of ICLR.
  25. Yu, M.; Yin, W.; Hasan, K. S.; Santos, C. d.; Xiang, B.; and Zhou, B. 2017. Improved neural relation detection for knowledge base question answering. In Proc. of ACL.

Cited by

Sorted by citations

Metadata

Authors
Wang, S., Yu, M., Guo, X., Wang, Z., Klinger, T., Zhang, W., Chang, S., Tesauro, G., Zhou, B., & Jiang, J.
Affiliations
  • Singapore Management University (SG)
  • IBM (United States) (US)
  • Jingdong (China) (CN)
ORCID
Venue
Proceedings of the AAAI Conference on Artificial Intelligence
Publisher
Association for the Advancement of Artificial Intelligence (AAAI)
Published
2018-04-26
Volume
32
Issue
1
Pages
5981-5988
ISSN
  • 2159-5399 (ISSN-L)
  • 2374-3468
DOI
10.1609/aaai.v32i1.12053
OpenAlex
W4289865932
Cited by
351
References
8
Citations by year
2025: 10 · 2024: 15 · 2023: 32 · 2022: 32 · 2021: 71 · 2020: 81 · 2019: 73 · 2018: 35
FWCI
23.09
Type
conference paper
Language
en
Open access
Locations
  • Proceedings of the AAAI Conference on Artificial Intelligence (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI)) (submittedVersion)
  • Singapore Management University Institutional Knowledge (InK) (Singapore Management University) (submittedVersion)
  • arXiv (Cornell University)
  • National Conference on Artificial Intelligence
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
  • Physical Sciences › Computer Science › Information Systems › Information Retrieval and Search Behavior
  • Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
Keywords
open-domain question answering, passage ranking, answer extraction, reinforcement learning, information retrieval, reading comprehension

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review