Learning to Correct Erroneous Words for Document Grounded Conversations | |
Junyan Qiu1,2![]() ![]() ![]() | |
2023-06 | |
会议名称 | International Conference on Software and Computer Applications |
会议日期 | 2023.02.23-2023.02.25 |
会议地点 | Kuantan, Malaysia |
出版者 | ACM |
摘要 | Document grounded conversation (DGC) aims to generate informative responses when talking about a document. It is normally formulated as a sequence-to-sequence (Seq2seq) learning problem, which directly maps source sequences, i.e., the context and background documents, to the target sequence, i.e., the response. These responses are normally used as the final output without further polishing, which may suffer from the global information loss owing to the auto-regression paradigm. To tackle this problem, some researches designed two-pass generation to improve the quality of responses. However, these approaches lack the capability of distinguishing inappropriate words in the first pass, which may maintain the erroneous words while rewrite the correct ones. In this paper, we design a scheduled error correction network (SECN) with multiple generation passes to explicitly locate and rewrite the erroneous words in previous passes. Specifically, a discriminator is employed to distinguish erroneous words which are further revised by a refiner. Moreover, we also apply curriculum learning with reasonable learning schedule to train our model from easy to hard conversations, where the complexity is measured by the number of decoding passes. We conduct comprehensive experiments on a public document grounded conversation dataset, Wizard-of-Wikipedia, and the results demonstrate significant promotions over several strong benchmarks. |
关键词 | Deep Learning Natural Language Generation Dialogue System Curriculum Learning |
学科门类 | 工学::计算机科学与技术(可授工学、理学学位) |
收录类别 | EI |
语种 | 英语 |
是否为代表性论文 | 否 |
七大方向——子方向分类 | 自然语言处理 |
国重实验室规划方向分类 | 语音语言处理 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/57412 |
专题 | 综合信息系统研究中心_视知觉融合及其应用 |
通讯作者 | Junyan Qiu |
作者单位 | 1.University of Chinese Academy of Sciences 2.Institute of Automation, Chinese Academy of Sciences 3.Meituan |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Junyan Qiu,Haitao Wang,Yiping Yang. Learning to Correct Erroneous Words for Document Grounded Conversations[C]:ACM,2023. |
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 | ||
3587828.3587883.pdf(773KB) | 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