| 机器阅读理解的研究进展 |
| |
| 引用本文： | 王小捷,白子薇,李可,袁彩霞. 机器阅读理解的研究进展[J]. 北京邮电大学学报, 2019, 42(6): 1-9. DOI: 10.13190/j.jbupt.2019-111 |
| |
| 作者姓名： | 王小捷 白子薇 李可 袁彩霞 |
| |
| 作者单位： | 北京邮电大学计算机学院,北京100876;北京邮电大学计算机学院,北京100876;北京邮电大学计算机学院,北京100876;北京邮电大学计算机学院,北京100876 |
| |
| 基金项目： | 国家自然科学基金项目（61906018） |
| |
| 摘 要： | 为便于厘清机器阅读理解任务的研究现状，按照答案来源，将机器阅读理解分为完形填空、片段选择、多项选择和答案生成4类.在统一的编码器-交互与推理-输出框架下对此4类任务的已有研究进行了综述，并描述了2种对此框架的可能扩展；最后讨论了机器阅读理解未来需要解决的问题.
|
| 关 键 词： | 机器阅读理解 编码器 交互 注意力机制 |
| 收稿时间： | 2019-06-11 |
Survey on Machine Reading Comprehension |
| |
| WANG Xiao-jie,BAI Zi-wei,LI Ke,YUAN Cai-xia. Survey on Machine Reading Comprehension[J]. Journal of Beijing University of Posts and Telecommunications, 2019, 42(6): 1-9. DOI: 10.13190/j.jbupt.2019-111 |
| |
| Authors: | WANG Xiao-jie BAI Zi-wei LI Ke YUAN Cai-xia |
| |
| Affiliation: | School of Computer Science, Beijing University of Posts and Telecommunications, Beijing 100876, China |
| |
| Abstract: | In order to make clear the recent work of machine reading comprehension (MRC) tasks, they are divided into four types of subtasks with different sources of answers. They are cloze-style, span selection, multi-choice, and answer generation. Previous work on these four different types of subtasks is investigated under a unified framework of encoder-interaction and reasoning-output. Two types of recent developments for the frame are also given. Several challenges on MRC for future work are discussed at the end of the survey. |
| |
| Keywords: | machine reading comprehension encoder interaction attention mechanism |
| 本文献已被 万方数据 等数据库收录！ |
| 点击此处可从《北京邮电大学学报》浏览原始摘要信息 |
|
点击此处可从《北京邮电大学学报》下载全文 |
|
