DUMA: Reading Comprehension with Transposition Thinking

Abstract

Multi-choice Machine Reading Comprehension (MRC) requires model to decide the correct answer from a set of answer options when given a passage and a question. Thus in addition to a powerful Pre-trained Language Model (PrLM) as encoder, multi-choice MRC especially relies on a matching network design which is supposed to effectively capture the relationships among the triplet of passage, question and answers. While the newer and more powerful PrLMs have shown their mightiness even without the support from a matching network, we propose a new DUal Multi-head Co-Attention (DUMA) model, which is inspired by human's transposition thinking process solving the multi-choice MRC problem: respectively considering each other's focus from the standpoint of passage and question. The proposed DUMA has been shown effective and is capable of generally promoting PrLMs. Our proposed method is evaluated on two benchmark multi-choice MRC tasks, DREAM and RACE, showing that in terms of powerful PrLMs, DUMA can still boost the model to reach new state-of-the-art performance.

References in corpus (6)

• AutoML: A Survey of the State-of-the-Art
• Modeling Multi-turn Conversation with Deep Utterance Aggregation
• Option Comparison Network for Multiple-choice Reading Comprehension
• Lingke: A Fine-grained Multi-turn Chatbot for Customer Service
• Convolutional Spatial Attention Model for Reading Comprehension with Multiple-Choice Questions
• A Deep Cascade Model for Multi-Document Reading Comprehension

Cited by in corpus (2)

• Improving Machine Reading Comprehension with Single-choice Decision and Transfer Learning
• XRJL-HKUST at SemEval-2021 Task 4: WordNet-Enhanced Dual Multi-head Co-Attention for Reading Comprehension of Abstract Meaning