Chains-of-Reasoning at TextGraphs 2019 Shared Task: Reasoning over Chains of Facts for Explainable Multi-hop Inference
Rajarshi Das, Ameya Godbole, Manzil Zaheer, Shehzaad Dhuliawala, Andrew McCallum
Abstract
This paper describes our submission to the shared task on “Multi-hop Inference Explanation Regeneration” in TextGraphs workshop at EMNLP 2019 (Jansen and Ustalov, 2019). Our system identifies chains of facts relevant to explain an answer to an elementary science examination question. To counter the problem of ‘spurious chains’ leading to ‘semantic drifts’, we train a ranker that uses contextualized representation of facts to score its relevance for explaining an answer to a question. Our system was ranked first w.r.t the mean average precision (MAP) metric outperforming the second best system by 14.95 points.- Anthology ID:
- D19-5313
- Volume:
- Proceedings of the Thirteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-13)
- Month:
- November
- Year:
- 2019
- Address:
- Hong Kong
- Venue:
- TextGraphs
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 101–117
- Language:
- URL:
- https://aclanthology.org/D19-5313
- DOI:
- 10.18653/v1/D19-5313
- Cite (ACL):
- Rajarshi Das, Ameya Godbole, Manzil Zaheer, Shehzaad Dhuliawala, and Andrew McCallum. 2019. Chains-of-Reasoning at TextGraphs 2019 Shared Task: Reasoning over Chains of Facts for Explainable Multi-hop Inference. In Proceedings of the Thirteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-13), pages 101–117, Hong Kong. Association for Computational Linguistics.
- Cite (Informal):
- Chains-of-Reasoning at TextGraphs 2019 Shared Task: Reasoning over Chains of Facts for Explainable Multi-hop Inference (Das et al., TextGraphs 2019)
- PDF:
- https://preview.aclanthology.org/starsem-semeval-split/D19-5313.pdf