Logic-Guided Data Augmentation and Regularization for Consistent Question Answering

Abstract

Many natural language questions require qualitative, quantitative or logical comparisons between two entities or events. This paper addresses the problem of improving the accuracy and consistency of responses to comparison questions by integrating logic rules and neural models. Our method leverages logical and linguistic knowledge to augment labeled training data and then uses a consistency-based regularizer to train the model. Improving the global consistency of predictions, our approach achieves large improvements over previous methods in a variety of question answering (QA) tasks including multiple-choice qualitative reasoning, cause-effect reasoning, and extractive machine reading comprehension. In particular, our method significantly improves the performance of RoBERTa-based models by 1-5% across datasets. We advance the state of the art by around 5-8% on WIQA and QuaRel and reduce consistency violations by 58% on HotpotQA. We further demonstrate that our approach can learn effectively from limited data.

Published as a conference paper at ACL 2020

References in corpus (7)

• SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
• fairseq: A Fast, Extensible Toolkit for Sequence Modeling
• Adversarial Examples Improve Image Recognition
• What Makes Reading Comprehension Questions Easier?
• VQA-LOL: Visual Question Answering under the Lens of Logic
• WIQA: A dataset for "What if..." reasoning over procedural text
• A Generate-Validate Approach to Answering Questions about Qualitative Relationships

Cited by in corpus (3)

• KnowDis: Knowledge Enhanced Data Augmentation for Event Causality Detection via Distant Supervision
• Leveraging Declarative Knowledge in Text and First-Order Logic for Fine-Grained Propaganda Detection
• Learn to Resolve Conversational Dependency: A Consistency Training Framework for Conversational Question Answering