| 基于Masked-Pointer的多轮对话重写模型 |
| |
| 引用本文： | 杨双涛,符博,于晨晨,胡长建.基于Masked-Pointer的多轮对话重写模型[J].北京大学学报(自然科学版),2021,57(1):31-37. |
| |
| 作者姓名： | 杨双涛 符博 于晨晨 胡长建 |
| |
| 作者单位： | 联想研究院人工智能实验室, 北京 100085 |
| |
| 摘 要： | 针对多轮会话中的Non-Sentential Utterances(NSUs)问题,结合当前在自然语言处理领域广泛使用的预训练语言模型,将Masked Language Model用于多轮会话NSUs的重写任务,提出Masked Rewriter Model.与基于Seq2Seq的重写模型相比,重写效果提升明显.根据N...
|
| 关 键 词： | 人机交互 预训练语言模型 指针网络 会话重写 |
| 收稿时间： | 2020-06-16 |
Multi-Turn Conversation Rewriter Model Based on Masked-Pointer |
| |
| YANG Shuangtao,FU Bo,YU Chenchen,HU Changjian.Multi-Turn Conversation Rewriter Model Based on Masked-Pointer[J].Acta Scientiarum Naturalium Universitatis Pekinensis,2021,57(1):31-37. |
| |
| Authors: | YANG Shuangtao FU Bo YU Chenchen HU Changjian |
| |
| Institution: | AI Lab, Lenovo Research, Beijing 100085 |
| |
| Abstract: | To solve the problem of Non-Sentential Utterances in multi-turn conversations, Masked Rewriter Model is proposed based on the Masked Language Model, and the rewriting performance is significantly improved compared with the Seq2Seq-based rewriting model. Considering the NSUs rewriting task characteristics, Masked-Pointer Rewriter Model is proposed based on the Masked Language Model and Pointer Network, which achieves better rewriting results than the Masked Rewriter Model by using the Pointer Network to enhance the model’s attention to historical information. |
| |
| Keywords: | human-computer interaction pre-trainied language model pointer network conversation rewrite |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《北京大学学报(自然科学版)》浏览原始摘要信息 |
| 点击此处可从《北京大学学报(自然科学版)》下载免费的PDF全文 |
