Attention-Based Convolutional Neural Network for Machine Comprehension

Abstract

Understanding open-domain text is one of the primary challenges in natural language processing (NLP). Machine comprehension benchmarks evaluate the system's ability to understand text based on the text content only. In this work, we investigate machine comprehension on MCTest, a question answering (QA) benchmark. Prior work is mainly based on feature engineering approaches. We come up with a neural network framework, named hierarchical attention-based convolutional neural network (HABCNN), to address this task without any manually designed features. Specifically, we explore HABCNN for this task by two routes, one is through traditional joint modeling of passage, question and answer, one is through textual entailment. HABCNN employs an attention mechanism to detect key phrases, key sentences and key snippets that are relevant to answering the question. Experiments show that HABCNN outperforms prior deep learning approaches by a big margin.

arXiv comment7 pages, 4 figures

References in corpus (4)

• Training Very Deep Networks
• Ask Me Anything: Dynamic Memory Networks for Natural Language Processing
• Deep Learning for Answer Sentence Selection
• Towards Neural Network-based Reasoning

Cited by in corpus (7)

• Machine Comprehension Using Match-LSTM and Answer Pointer
• End-to-End Answer Chunk Extraction and Ranking for Reading Comprehension
• Learning for Biomedical Information Extraction: Methodological Review of Recent Advances
• A Parallel-Hierarchical Model for Machine Comprehension on Sparse Data
• A Co-Matching Model for Multi-choice Reading Comprehension
• Mining Significant Microblogs for Misinformation Identification: An Attention-based Approach
• CAESAR: Context Awareness Enabled Summary-Attentive Reader