Discrete Reasoning Templates for Natural Language Understanding
Al-Negheimish, Hadeel, Madhyastha, Pranava, Russo, Alessandra
–arXiv.org Artificial Intelligence
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
arXiv.org Artificial Intelligence
Apr-5-2021
- Country:
- Oceania > Australia
- North America > United States
- Texas (0.04)
- Minnesota > Hennepin County
- Minneapolis (0.14)
- Louisiana > Orleans Parish
- New Orleans (0.04)
- Europe > Italy
- Asia > China
- Hong Kong (0.05)
- Genre:
- Research Report (0.82)
- Industry:
- Education (0.71)
- Technology: