A Co-Matching Model for Multi-choice Reading Comprehension
arXiv:1806.04068
Abstract
Multi-choice reading comprehension is a challenging task, which involves the matching between a passage and a question-answer pair. This paper proposes a new co-matching approach to this problem, which jointly models whether a passage can match both a question and a candidate answer. Experimental results on the RACE dataset demonstrate that our approach achieves state-of-the-art performance.
arXiv comment6, accepted ACL 2018
References in corpus (9)
- Teaching Machines to Read and Comprehend
- SQuAD: 100,000+ Questions for Machine Comprehension of Text
- The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations
- Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering
- A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task
- RACE: Large-scale ReAding Comprehension Dataset From Examinations
- A Parallel-Hierarchical Model for Machine Comprehension on Sparse Data
- Dynamic Fusion Networks for Machine Reading Comprehension
- Attention-Based Convolutional Neural Network for Machine Comprehension
Cited by in corpus (11)
- Option Comparison Network for Multiple-choice Reading Comprehension
- Dual Co-Matching Network for Multi-choice Reading Comprehension
- How Does NLP Benefit Legal System: A Summary of Legal Artificial Intelligence
- Generating Distractors for Reading Comprehension Questions from Real Examinations
- Do Multi-hop Readers Dream of Reasoning Chains?
- LogiQA: A Challenge Dataset for Machine Reading Comprehension with Logical Reasoning
- JEC-QA: A Legal-Domain Question Answering Dataset
- GenNet : Reading Comprehension with Multiple Choice Questions using Generation and Selection model
- Knowledge Efficient Deep Learning for Natural Language Processing
- Feudal Reinforcement Learning by Reading Manuals
- Asymmetrical Hierarchical Networks with Attentive Interactions for Interpretable Review-Based Recommendation