Convolutional Spatial Attention Model for Reading Comprehension with Multiple-Choice Questions

By Z. Chen, Yiming Cui, Wentao Ma, Shijin Wang, Guoping Hu. 2018

31 citations recorded by the source corpus.

Machine Reading Comprehension (MRC) with multiplechoice 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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Zhiyuan Liu
2. Maosong Sun
3. Yejin Choi
4. Mohit Bansal
5. Jianfeng Gao
6. Zhuosheng Zhang
7. Dong Yu
8. Jianshu Chen

In Computer Vision and Pattern Recognition

1. Zhiyuan Liu
2. Maosong Sun
3. Jianshu Chen
4. Dong Yu
5. Claire Cardie
6. Cunchao Tu
7. Dian Yu
8. Kai Sun

In Natural Language Processing

1. Zhuosheng Zhang
2. Zhiyuan Liu
3. Maosong Sun
4. Dong Yu
5. Yejin Choi
6. Dian Yu
7. Kai Sun
8. Jianshu Chen

Citations in the corpus

• Dual Co-Matching Network for Multi-choice Reading Comprehension (2019, background): “However, previous matching strategies fraught with obvious shortcomings (Wang et al., 2018; Tang et al., 2019; Chen et al., 2018; Ran et al., 2019) are usually unidirectional which only calculate question-aware passage representation and ignore passage-aware question representation when modeling the”
• DREAM: A Challenge Data Set and Models for Dialogue-Based Reading Comprehension (2019, methodology): “…adding ELMo representations (Peters et al., 2018) as additional features to a neural model since recent studies show that directly fine-tuning a pre-trained language model such as FTLM is significantly superior on multiple-choice reading comprehension tasks (Radford et al., 2018; Chen et al., 2019).”
• JEC-QA: A Legal-Domain Question Answering Dataset (2019, background): “Convolutional Spatial Attention (CSA) (Chen et al. 2019) first generates enriched representations of passages, candidate answers, and questions with attention mechanism, and then applies CNN-MaxPooling operation to summarize adjacent attention information.”