Using Natural Language Relations between Answer Choices for Machine Comprehension
This work addresses the problem of improving machine comprehension accuracy for question answering systems by incorporating inter-choice relationships, which is an incremental improvement to existing methods.
This paper proposes a method to improve machine comprehension by leveraging natural language relations like entailment and contradiction between answer choices. It uses an Integer Linear Programming (ILP)-based relational framework to re-evaluate decisions from a standalone QA system based on relations identified by a Natural Language Inference (NLI) system.
When evaluating an answer choice for Reading Comprehension task, other answer choices available for the question and the answers of related questions about the same paragraph often provide valuable information. In this paper, we propose a method to leverage the natural language relations between the answer choices, such as entailment and contradiction, to improve the performance of machine comprehension. We use a stand-alone question answering (QA) system to perform QA task and a Natural Language Inference (NLI) system to identify the relations between the choice pairs. Then we perform inference using an Integer Linear Programming (ILP)-based relational framework to re-evaluate the decisions made by the standalone QA system in light of the relations identified by the NLI system. We also propose a multitask learning model that learns both the tasks jointly.