Declarative Question Answering over Knowledge Bases containing Natural Language Text with Answer Set Programming
This addresses the problem of scalable logical reasoning for question answering over large natural language text, though it appears incremental as it builds on existing ASP and NLP methods.
The paper tackles the challenge of question answering when additional knowledge is needed, by proposing an approach that uses Answer Set Programming (ASP) to perform logical reasoning over natural language text, achieving up to 18% performance gain compared to standard MCQ solvers.
While in recent years machine learning (ML) based approaches have been the popular approach in developing end-to-end question answering systems, such systems often struggle when additional knowledge is needed to correctly answer the questions. Proposed alternatives involve translating the question and the natural language text to a logical representation and then use logical reasoning. However, this alternative falters when the size of the text gets bigger. To address this we propose an approach that does logical reasoning over premises written in natural language text. The proposed method uses recent features of Answer Set Programming (ASP) to call external NLP modules (which may be based on ML) which perform simple textual entailment. To test our approach we develop a corpus based on the life cycle questions and showed that Our system achieves up to $18\%$ performance gain when compared to standard MCQ solvers.