Abstract
This work deals with the challenge of learning and reasoning over multi-hop question answering (QA). We propose a graph reasoning network based on the semantic structure of the sentences to learn cross paragraph reasoning paths and find the supporting facts and the answer jointly. The proposed graph is a heterogeneous document-level graph that contains nodes of type sentence (question, title, and other sentences), and semantic role labeling sub-graphs per sentence that contain arguments as nodes and predicates as edges. Incorporating the argument types, the argument phrases, and the semantics of the edges originated from SRL predicates into the graph encoder helps in finding and also the explainability of the reasoning paths. Our proposed approach shows competitive performance on the HotpotQA distractor setting benchmark compared to the recent state-of-the-art models.- Anthology ID:
- 2020.emnlp-main.714
- 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:
- 8881–8891
- Language:
- URL:
- https://aclanthology.org/2020.emnlp-main.714
- DOI:
- 10.18653/v1/2020.emnlp-main.714
- Cite (ACL):
- Chen Zheng and Parisa Kordjamshidi. 2020. SRLGRN: Semantic Role Labeling Graph Reasoning Network. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 8881–8891, Online. Association for Computational Linguistics.
- Cite (Informal):
- SRLGRN: Semantic Role Labeling Graph Reasoning Network (Zheng & Kordjamshidi, EMNLP 2020)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/2020.emnlp-main.714.pdf
- Code
- HLR/SRLGRN
- Data
- HotpotQA, TriviaQA, WikiHop