Abstract
Creating explanations for answers to science questions is a challenging task that requires multi-hop inference over a large set of fact sentences. This year, to refocus the Textgraphs Shared Task on the problem of gathering relevant statements (rather than solely finding a single ‘correct path’), the WorldTree dataset was augmented with expert ratings of ‘relevance’ of statements to each overall explanation. Our system, which achieved second place on the Shared Task leaderboard, combines initial statement retrieval; language models trained to predict the relevance scores; and ensembling of a number of the resulting rankings. Our code implementation is made available at https://github.com/mdda/worldtree_corpus/tree/textgraphs_2021- Anthology ID:
- 2021.textgraphs-1.20
- Volume:
- Proceedings of the Fifteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-15)
- Month:
- June
- Year:
- 2021
- Address:
- Mexico City, Mexico
- Venue:
- TextGraphs
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 176–180
- Language:
- URL:
- https://aclanthology.org/2021.textgraphs-1.20
- DOI:
- 10.18653/v1/2021.textgraphs-1.20
- Cite (ACL):
- Sureshkumar Vivek Kalyan, Sam Witteveen, and Martin Andrews. 2021. Textgraphs-15 Shared Task System Description : Multi-Hop Inference Explanation Regeneration by Matching Expert Ratings. In Proceedings of the Fifteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-15), pages 176–180, Mexico City, Mexico. Association for Computational Linguistics.
- Cite (Informal):
- Textgraphs-15 Shared Task System Description : Multi-Hop Inference Explanation Regeneration by Matching Expert Ratings (Vivek Kalyan et al., TextGraphs 2021)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2021.textgraphs-1.20.pdf
- Code
- mdda/worldtree_corpus