Knowledge Commons of Institute of Automation,CAS
Reconstructed Option Rereading Network For Opinion Questions Reading Comprehension | |
Delai Qiu1; Liang Bao1; Zhixing Tian2,3; Yuanzhe Zhang3; Kang Liu2,3; Jun Zhao2,3; Xiangwen Liao1 | |
2019 | |
会议名称 | China National Conference on Chinese Computational Linguistics |
会议日期 | 2019 |
会议地点 | China |
摘要 | Multiple-choice reading comprehension task has seen a recent surge of popularity, aiming at choosing the correct option from candidate options for the question referring to a related passage. Previous work focuses on factoid-based questions but ignore opinion-based questions. Options of opinion-based questions are usually sentiment phrases, such as “Good” or “Bad”. It causes that previous work fail to model the interactive information among passage, question and options, because their approaches are based on the premise that options contain rich semantic information. To this end, we propose a Reconstructed Option Rereading Network (RORN) to tackle it. We first reconstruct the options based on question. Then, the model utilize the reconstructed options to generate the representation of options. Finally, we fed into a max-pooling layer to obtain the ranking score for each opinion. Experiments show that our proposed achieve state-of-art performance on the Chinese opinion questions machine reading comprehension datasets in AI challenger competition. |
语种 | 英语 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/44824 |
专题 | 多模态人工智能系统全国重点实验室_自然语言处理 |
通讯作者 | Delai Qiu |
作者单位 | 1.College of Mathematics and Computer Science 2.University of Chinese Academy of Sciences 3.National Laboratory of Pattern Recognition, Institute of Automation, Academy of Sciences |
推荐引用方式 GB/T 7714 | Delai Qiu,Liang Bao,Zhixing Tian,et al. Reconstructed Option Rereading Network For Opinion Questions Reading Comprehension[C],2019. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
opinionmrc.pdf(437KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论