Multi-Passage Machine Reading Comprehension with Cross-Passage Answer Verification

Abstract

Machine reading comprehension (MRC) on real web data usually requires the machine to answer a question by analyzing multiple passages retrieved by search engine. Compared with MRC on a single passage, multi-passage MRC is more challenging, since we are likely to get multiple confusing answer candidates from different passages. To address this problem, we propose an end-to-end neural model that enables those answer candidates from different passages to verify each other based on their content representations. Specifically, we jointly train three modules that can predict the final answer based on three factors: the answer boundary, the answer content and the cross-passage answer verification. The experimental results show that our method outperforms the baseline by a large margin and achieves the state-of-the-art performance on the English MS-MARCO dataset and the Chinese DuReader dataset, both of which are designed for MRC in real-world settings.

10 pages, ACL 2018 camera-ready version

References in corpus (19)

• Adam: A Method for Stochastic Optimization
• Teaching Machines to Read and Comprehend
• An Overview of Multi-Task Learning in Deep Neural Networks
• Bidirectional Attention Flow for Machine Comprehension
• SQuAD: 100,000+ Questions for Machine Comprehension of Text
• The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations
• Dynamic Coattention Networks For Question Answering
• Machine Comprehension Using Match-LSTM and Answer Pointer
• SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine
• ReasoNet: Learning to Stop Reading in Machine Comprehension
• Adversarial Examples for Evaluating Reading Comprehension Systems
• Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering
• A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task
• R${}^3$: Reinforced Reader-Ranker for Open-Domain Question Answering
• DCN+: Mixed Objective and Deep Residual Coattention for Question Answering
• MEMEN: Multi-layer Embedding with Memory Networks for Machine Comprehension
• DuReader: a Chinese Machine Reading Comprehension Dataset from Real-world Applications
• S-Net: From Answer Extraction to Answer Generation for Machine Reading Comprehension
• Making Neural QA as Simple as Possible but not Simpler

Cited by in corpus (4)

• Knowledge-Aided Open-Domain Question Answering
• A Study of the Tasks and Models in Machine Reading Comprehension
• CHIME: Cross-passage Hierarchical Memory Network for Generative Review Question Answering
• Exploiting Sentence Embedding for Medical Question Answering