Knowledge Commons of Institute of Automation,CAS
Generating Questions for Knowledge Bases via Incorporating Diversified Contexts and Answer-Aware Loss | |
Liu, Cao1,2![]() ![]() ![]() ![]() | |
2019-11 | |
会议名称 | the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) |
会议日期 | November 3–7, 2019 |
会议地点 | Hong Kong, China |
摘要 | We tackle the task of question generation over knowledge bases. Conventional methods for this task neglect two crucial research issues: 1) the given predicate needs to be expressed; 2) the answer to the generated question needs to be definitive. In this paper, we strive toward the above two issues via incorporating diversified contexts and answer-aware loss. Specifically, we propose a neural encoder-decoder model with multi-level copy mechanisms to generate such questions. Furthermore, the answer aware loss is introduced to make generated questions corresponding to more definitive answers. Experiments demonstrate that our model achieves state-of-the-art performance. Meanwhile, such generated question can express the given predicate and correspond to a definitive answer |
七大方向——子方向分类 | 自然语言处理 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/39186 |
专题 | 多模态人工智能系统全国重点实验室_自然语言处理 |
作者单位 | 1.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences 2.University of Chinese Academy of Sciences 3.Alibaba AI Labs |
第一作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Liu, Cao,Liu, Kang,He, Shizhu,et al. Generating Questions for Knowledge Bases via Incorporating Diversified Contexts and Answer-Aware Loss[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 | ||
EMNLP2019-Cao Liu.pd(602KB) | 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