Consensus Attention-based Neural Networks for Chinese Reading Comprehension

Abstract

Reading comprehension has embraced a booming in recent NLP research. Several institutes have released the Cloze-style reading comprehension data, and these have greatly accelerated the research of machine comprehension. In this work, we firstly present Chinese reading comprehension datasets, which consist of People Daily news dataset and Children's Fairy Tale (CFT) dataset. Also, we propose a consensus attention-based neural network architecture to tackle the Cloze-style reading comprehension problem, which aims to induce a consensus attention over every words in the query. Experimental results show that the proposed neural network significantly outperforms the state-of-the-art baselines in several public datasets. Furthermore, we setup a baseline for Chinese reading comprehension task, and hopefully this would speed up the process for future research.

9+1 pages, published at COLING 2016

References in corpus (1)

• A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task

Cited by in corpus (12)

• Attention in Natural Language Processing
• Machine Comprehension Using Match-LSTM and Answer Pointer
• Embracing data abundance: BookTest Dataset for Reading Comprehension
• DuReader: a Chinese Machine Reading Comprehension Dataset from Real-world Applications
• End-to-End Answer Chunk Extraction and Ranking for Reading Comprehension
• Subword-augmented Embedding for Cloze Reading Comprehension
• Discriminative Sentence Modeling for Story Ending Prediction
• HFL-RC System at SemEval-2018 Task 11: Hybrid Multi-Aspects Model for Commonsense Reading Comprehension
• Dataset for the First Evaluation on Chinese Machine Reading Comprehension
• LSICC: A Large Scale Informal Chinese Corpus
• Contextual Recurrent Units for Cloze-style Reading Comprehension
• Dependent Gated Reading for Cloze-Style Question Answering