Combining Natural Logic and Shallow Reasoning for Question Answering
2016pp. 442–452
Citations Over TimeTop 10% of 2016 papers
Abstract
Broad domain question answering is often difficult in the absence of structured knowledge bases, and can benefit from shallow lexical methods (broad coverage) and logical reasoning (high precision). We propose an approach for incorporating both of these signals in a unified framework based on natural logic. We extend the breadth of inferences afforded by natural logic to include relational entailment (e.g., buy own) and meronymy (e.g., a person born in a city is born the city's country). Furthermore, we train an evaluation function -akin to gameplayingto evaluate the expected truth of candidate premises on the fly. We evaluate our approach on answering multiple choice science questions, achieving strong results on the dataset.
Related Papers
- → A survey on textual entailment based question answering(2021)20 cited
- → Logic-based approach for improving Arabic question answering(2014)10 cited
- → ARS_NITK at MEDIQA 2019:Analysing Various Methods for Natural Language Inference, Recognising Question Entailment and Medical Question Answering System(2019)12 cited
- → Semantics and complexity of abduction from default theories(1997)3 cited
- → Improving Question Answering Tasks by Textual Entailment Recognition(2008)2 cited