정보처리학회논문지:소프트웨어 및 데이터공학 (KIPS Transactions on Software and Data Engineering)

  • 제10권8호
  • /
  • Pages.319-330
  • /
  • 2021
  • /
  • 2287-5905(pISSN)
  • /
  • 2734-0503(eISSN)
한국정보처리학회 (Korea Information Processing Society)
권호 표지
DOI QR코드

DOI QR Code

다중 작업, 다중 홉 질문 응답을 위한 그래프 추론 및 맥락 융합

Graph Reasoning and Context Fusion for Multi-Task, Multi-Hop Question Answering

  • 투고 : 2021.04.12
  • 심사 : 2021.05.06
  • 발행 : 2021.08.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

최근 오픈 도메인 자연어 질문 응답 분야에서는 다중 작업, 다중 홉 질문 응답에 관한 연구들이 활발히 진행되어 오고 있다. 본 논문에서는 이러한 다중 작업, 다중 홉 질문들에 효과적으로 응답하기 위해, 계층적 그래프 기반의 새로운 심층 신경망 모델을 제안한다. 제안 모델에서는 계층적 그래프와 그래프 신경망을 이용해 여러 문단들로부터 서로 다른 수준의 맥락 정보를 얻어낸 후, 이들을 활용하여 답변 유형, 뒷받침 문장들과 답변 영역 등을 동시에 예측해낸다. 본 논문에서는 오픈 도메인 자연어 질문 응답 데이터 집합인 HotpotQA를 이용한 실험들을 통해, 제안 모델의 높은 성능과 긍정적 효과를 입증한다.

Recently, in the field of open domain natural language question answering, multi-task, multi-hop question answering has been studied extensively. In this paper, we propose a novel deep neural network model using hierarchical graphs to answer effectively such multi-task, multi-hop questions. The proposed model extracts different levels of contextual information from multiple paragraphs using hierarchical graphs and graph neural networks, and then utilize them to predict answer type, supporting sentences and answer spans simultaneously. Conducting experiments with the HotpotQA benchmark dataset, we show high performance and positive effects of the proposed model.

키워드

과제정보

이 연구는 2021년도 산업통상자원부 및 산업기술평가관리원(KEIT) 연구비 지원에 의한 연구임('10077538').

참고문헌

  1. Z. Yang, P. Qi, S. Zhang, Y. Bengio, W. Cohen, R. Salakhutdinov, and C. D. Manning, "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, pp.2369-2380, 2018.
  2. L. Qiu, Y. Xiao, Y. Qu, H. Zhou, L. Li, W. Zhang, and Y. Yu, "Dynamically fused graph network for multi-hop reasoning," In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy, pp.6140-6150, 2019.
  3. M. Zhang, F. Li, Y. Wang, Z. Zhang, Y. Zhou, and X. Li, "Coarse and fine granularity graph reasoning for interpretable multi-hop question answering," IEEE Access, Vol.8, pp.56755-56765, 2020. https://doi.org/10.1109/ACCESS.2020.2981134
  4. J. Devlin, M. W. Chang, K. Lee, and K. Toutanova, "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, Minneapolis, Minnesota, pp.4171-4186, 2019.
  5. A. Asai, K. Hashimoto, H. Hajishirzi, R. Socher, and C. Xiong, "Learning to retrieve reasoning paths over Wikipedia graph for question answering," In Proceedings of International Conference on Learning Representation, 2020.
  6. Y. Fang, S. Sun, Z. Gan, R. Pillai, S. Wang, and J. Liu, "Hierarchical graph network for multi-hop question answering," In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, pp.8823-8838, 2020.
  7. J. Welbl, P. Stenetorp, and S. Riedel, "Constructing datasets for multi-hop reading comprehension across documents," Transactions of the Association for Computational Linguistics, Vol.6, pp.287-302, 2018. https://doi.org/10.1162/tacl_a_00021
  8. Y. Liu, et al., "RoBERTa: A robustly optimized BERT pretraining approach," arxiv.org/abs/1907.11692, 2019.
  9. T. Mikolov, K. Chen, G. Corrado, and J. Dean, "Efficient estimation of word representations in vector space," In Proceedings of International Conference on Learning Representation, 2013.
  10. J. Pennington, R. Socher, and C. Manning, "GloVe: Global vectors for word representation," In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, Doha, Qatar, pp.1532-1543, 2014.
  11. A. Vaswani, et al., "Attention is all you need," In Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, California, pp.6000-6010, 2017.
  12. K. Nishida, K. Nishida, M. Nagata, A. Otsuka, I. Saito, H. Asano, and J. Tomita, "Answering while summarizing: Multi-task learning for multi-hop QA with evidence extraction," In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy, pp.2335-2345, 2019.
  13. T. N. Kipf and M. Welling, "Semi-supervised classification with graph convolutional networks," In Proceedings of the 5th International Conference on Learning Representations, Toulon, France, 2017.
  14. P. Velickovic, G. Cucurull, A. Casanova, A. Romero, P. Lio, and Y. Bengio, "Graph attention networks," In Proceedings of the 6th International Conference on Learning Representations, Vancouver, Canada, 2018.
  15. M. Tu, G. Wang, J. Huang, Y. Tang, X. He, and B. Zhou, "Multi-hop reading comprehension across multiple documents by reasoning over heterogeneous graphs," In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, pp.2704-2713, 2019.
  16. M. Tu, K. Huang, G. Wang, J. Huang, X. He, and B. Zhou, "Select, answer and explain: Interpretable multi-hop reading comprehension over multiple documents," In Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, New York, USA, pp.9073-9080, 2020.
  17. N. D. Cao, W. Aziz, and I. Titov, "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, Minneapolis, Minnesota, pp.2306-2317, 2019.
  18. Z. Lan, M. Chen, S. Goodman, K. Gimpel, P. Sharma, and R. Soricut, "ALBERT: A lite BERT for self-supervised learning of language representations," In Proceedings of International Conference on Learning Representation, 2020.
  19. M. Seo, A. Kembhavi, A. Farhadi, and H. Hajishirzi, "Bidirectional attention flow for machine comprehension," In Proceedings of International Conference on Learning Representation, 2017.