Abstract
Reasoning about information from multiple parts of a passage to derive an answer is an open challenge for reading-comprehension models. In this paper, we present an approach that reasons about complex questions by decomposing them to simpler subquestions that can take advantage of single-span extraction reading-comprehension models, and derives the final answer according to instructions in a predefined reasoning template. We focus on subtraction based arithmetic questions and evaluate our approach on a subset of the DROP dataset. We show that our approach is competitive with the state of the art while being interpretable and requires little supervision.- Anthology ID:
- 2021.eacl-srw.12
- Volume:
- Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop
- Month:
- April
- Year:
- 2021
- Address:
- Online
- Venue:
- EACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 80–87
- Language:
- URL:
- https://aclanthology.org/2021.eacl-srw.12
- DOI:
- 10.18653/v1/2021.eacl-srw.12
- Cite (ACL):
- Hadeel Al-Negheimish, Pranava Madhyastha, and Alessandra Russo. 2021. Discrete Reasoning Templates for Natural Language Understanding. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop, pages 80–87, Online. Association for Computational Linguistics.
- Cite (Informal):
- Discrete Reasoning Templates for Natural Language Understanding (Al-Negheimish et al., EACL 2021)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/2021.eacl-srw.12.pdf
- Data
- DROP, SQuAD