Convolutional Spatial Attention Model for Reading Comprehension with Multiple-Choice Questions
arXiv:1811.08610 · doi:10.1609/aaai.v33i01.33016276
Abstract
Machine Reading Comprehension (MRC) with multiple-choice questions requires the machine to read given passage and select the correct answer among several candidates. In this paper, we propose a novel approach called Convolutional Spatial Attention (CSA) model which can better handle the MRC with multiple-choice questions. The proposed model could fully extract the mutual information among the passage, question, and the candidates, to form the enriched representations. Furthermore, to merge various attention results, we propose to use convolutional operation to dynamically summarize the attention values within the different size of regions. Experimental results show that the proposed model could give substantial improvements over various state-of-the-art systems on both RACE and SemEval-2018 Task11 datasets.
arXiv comment8 pages. Accepted as a conference paper at AAAI-19 Technical Track
References in corpus (16)
- Adam: A Method for Stochastic Optimization
- TensorFlow: A system for large-scale machine learning
- Teaching Machines to Read and Comprehend
- NLTK: The Natural Language Toolkit
- Bidirectional Attention Flow for Machine Comprehension
- SQuAD: 100,000+ Questions for Machine Comprehension of Text
- Highway Networks
- The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations
- Dynamic Coattention Networks For Question Answering
- QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension
- FusionNet: Fusing via Fully-Aware Attention with Application to Machine Comprehension
- A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task
- RACE: Large-scale ReAding Comprehension Dataset From Examinations
- Dynamic Fusion Networks for Machine Reading Comprehension
- HFL-RC System at SemEval-2018 Task 11: Hybrid Multi-Aspects Model for Commonsense Reading Comprehension
- Yuanfudao at SemEval-2018 Task 11: Three-way Attention and Relational Knowledge for Commonsense Machine Comprehension
Cited by in corpus (6)
- Machine Reading Comprehension: The Role of Contextualized Language Models and Beyond
- DUMA: Reading Comprehension with Transposition Thinking
- Dual Co-Matching Network for Multi-choice Reading Comprehension
- Neural Machine Reading Comprehension: Methods and Trends
- JEC-QA: A Legal-Domain Question Answering Dataset
- GenNet : Reading Comprehension with Multiple Choice Questions using Generation and Selection model