MMM: Multi-stage Multi-task Learning for Multi-choice Reading Comprehension

Abstract

Machine Reading Comprehension (MRC) for question answering (QA), which aims to answer a question given the relevant context passages, is an important way to test the ability of intelligence systems to understand human language. Multiple-Choice QA (MCQA) is one of the most difficult tasks in MRC because it often requires more advanced reading comprehension skills such as logical reasoning, summarization, and arithmetic operations, compared to the extractive counterpart where answers are usually spans of text within given passages. Moreover, most existing MCQA datasets are small in size, making the learning task even harder. We introduce MMM, a Multi-stage Multi-task learning framework for Multi-choice reading comprehension. Our method involves two sequential stages: coarse-tuning stage using out-of-domain datasets and multi-task learning stage using a larger in-domain dataset to help model generalize better with limited data. Furthermore, we propose a novel multi-step attention network (MAN) as the top-level classifier for this task. We demonstrate MMM significantly advances the state-of-the-art on four representative MCQA datasets.

Accepted by AAAI 2020

References in corpus (10)

• Teaching Machines to Read and Comprehend
• SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine
• Sentence Encoders on STILTs: Supplementary Training on Intermediate Labeled-data Tasks
• Multi-Task Deep Neural Networks for Natural Language Understanding
• HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
• RACE: Large-scale ReAding Comprehension Dataset From Examinations
• Dynamically Fused Graph Network for Multi-hop Reasoning
• Stochastic Answer Networks for Machine Reading Comprehension
• Dialogue Natural Language Inference
• Supervised and Unsupervised Transfer Learning for Question Answering

Cited by in corpus (8)

• ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning
• Machine Reading Comprehension: The Role of Contextualized Language Models and Beyond
• From Machine Reading Comprehension to Dialogue State Tracking: Bridging the Gap
• Connecting the Dots: Detecting Adversarial Perturbations Using Context Inconsistency
• Reading Comprehension as Natural Language Inference: A Semantic Analysis
• Knowledgeable Dialogue Reading Comprehension on Key Turns
• Multi-turn Dialogue Reading Comprehension with Pivot Turns and Knowledge
• Deep Neural Networks with Short Circuits for Improved Gradient Learning