Abstract
Recently, attempting to model texts as graph structure and introducing graph neural networks to deal with it has become a trend in many NLP research areas. In this paper, we investigate whether the graph structure is necessary for textual multi-hop reasoning. Our analysis is centered on HotpotQA. We construct a strong baseline model to establish that, with the proper use of pre-trained models, graph structure may not be necessary for textual multi-hop reasoning. We point out that both graph structure and adjacency matrix are task-related prior knowledge, and graph-attention can be considered as a special case of self-attention. Experiments demonstrate that graph-attention or the entire graph structure can be replaced by self-attention or Transformers.- Anthology ID:
- 2020.emnlp-main.583
- Volume:
- Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
- Month:
- November
- Year:
- 2020
- Address:
- Online
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 7187–7192
- Language:
- URL:
- https://aclanthology.org/2020.emnlp-main.583
- DOI:
- 10.18653/v1/2020.emnlp-main.583
- Cite (ACL):
- Nan Shao, Yiming Cui, Ting Liu, Shijin Wang, and Guoping Hu. 2020. Is Graph Structure Necessary for Multi-hop Question Answering?. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 7187–7192, Online. Association for Computational Linguistics.
- Cite (Informal):
- Is Graph Structure Necessary for Multi-hop Question Answering? (Shao et al., EMNLP 2020)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2020.emnlp-main.583.pdf
- Data
- HotpotQA