Using Natural Language Relations between Answer Choices for Machine Comprehension

By Rajkumar Pujari, Dan Goldwasser. 2019

5 citations recorded by the source corpus.

While 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.

Subfields: Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

1. Zhuosheng Zhang
2. Yuwei Wu
3. Xi Zhou
4. Xiaoping Zhou
5. Zhao Hai
6. Shuailiang Zhang
7. Hai Zhao
8. Junjie Yang

Citations in the corpus

• Dual Co-Matching Network for Multi-choice Reading Comprehension (2019, background): “formance decrease in most cases. Most recent works attempting to integrate answer option interaction information focus on building attention mechanism at word-level (Ran et al. 2019; Zhu et al. 2018; Pujari and Goldwasser 2019) whose performance increase is very limited. Our answer option interactio”