Utterance Rewriter
解决指代消解与信息省略问题
-
Hui Su, Xiaoyu Shen, Rongzhi Zhang, Fei Sun, Pengwei Hu, Cheng Niu, and Jie Zhou. 2019. Improving Multi-turn Dialogue Modelling with Utterance ReWriter.arXiv preprint arXiv:1906.07004 (2019).
-
Svitlana Vakulenko, Shayne Longpre, Zhucheng Tu, and Raviteja Anantha. 2020. Question Rewriting for Conversational Question Answering. ArXivabs/2004.14652 (2020).
-
Ahmed Elgohary, Denis Peskov, and Jordan L. BoydGraber. 2019. Can you unpack that? learning to
rewrite questions-in-context. In EMNLP.
-
Few-Shot Generative Conversational Query Rewriting
Pointer Networkers
问题形式化
训练样本：\((H, U_n -> R)\)
前n-1轮对话：\(H = \{U_1, U_2,...,U_{N-1}\}\)
第n轮话述，即要改写的话述：\(U_n\)
改写以后的话述：\(R\)，如果不存在指代消解和实体省略情况，\(R\)就等同于\(U_n\)，即负样本。
目标：学习映射函数\(p(R|(H, U_N))\)，自动根据历史信息\(H\)重写\(U_n\)。
Share on:
Twitter
❄ Facebook
❄ Email