Knowledge Commons of Institute of Automation,CAS
Curriculum Learning for Natural Answer Generation | |
Liu, Cao1,2; He, Shizhu1; Liu, Kang1,2; Zhao, Jun1,2 | |
2018-07 | |
会议名称 | The Twenty-Seventh International Joint Conference on Artificial Intelligence (IJCAI-18) |
会议日期 | July 13-19, 2018 |
会议地点 | Stockholm, Sweden |
摘要 | By reason of being able to obtain natural language responses, natural answers are more favored in real-world Question Answering (QA) systems. Generative models learn to automatically generate natural answers from large-scale question answer pairs (QA-pairs). However, they are suffering from the uncontrollable and uneven quality of QA-pairs crawled from the Internet. To address this problem, we propose a curriculum learning based framework for natural answer generation (CL-NAG), which is able to take full advantage of the valuable learning data from a noisy and uneven-quality corpora. Specifically, we employ two practical measures to automatically measure the quality (complexity) of QA-pairs. Based on the measurements, CLNAG firstly utilizes simple and low-quality QApairs to learn a basic model, and then gradually learns to produce better answers with richer contents and more complete syntaxes based on more complex and higher-quality QA-pairs. In this way, all valuable information in the noisy and unevenquality corpora could be fully exploited. Experiments demonstrate that CL-NAG outperforms the state-of-the-art, which increases 6.8% and 8.7% in the accuracy for simple and complex questions, respectively. |
语种 | 英语 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/39190 |
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 |
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,He, Shizhu,Liu, Kang,et al. Curriculum Learning for Natural Answer Generation[C],2018. |
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 | ||
IJCAI2018-Cao Liu.pd(368KB) | 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