arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2106.15903cs.CLcs.IR
收藏

通过优化Levenshtein距离学习会话提问

Learning to Ask Conversational Questions by Optimizing Levenshtein Distance

Shandong University(山东大学);University of Amsterdam(阿姆斯特丹大学);Ahold Delhaize(皇家阿霍德德尔海兹集团);Sinovation Ventures(创新工场)

Zhongkun Liu, Pengjie Ren, Zhumin Chen, Zhaochun Ren, Maarten de Rijke, Ming Zhou

摘要:

会话问题简化(CQS)旨在通过整合一些会话特征,将自包含的问题简化为会话问题,例如,回指和省略。现有的基于最大似然估计(MLE)的方法经常被困在容易学习的标记中,因为在训练过程中所有标记都被平等对待。在这项工作中,我们引入了一个强化迭代序列编辑(RISE)框架,通过显式编辑操作优化最小Levenshtein距离(MLD)。RISE能够关注与会话特征相关的标记。为了训练RISE,我们设计了一种迭代强化训练(IRT)算法,并采用基于动态规划的采样(DPS)过程来提高探索性。在两个基准数据集上的实验结果表明,RISE的性能显着优于最先进的方法,并且在看不见的数据上具有很好的泛化能力。

英文摘要:

Conversational Question Simplification (CQS) aims to simplify self-contained questions into conversational ones by incorporating some conversational characteristics, e.g., anaphora and ellipsis. Existing maximum likelihood estimation (MLE) based methods often get trapped in easily learned tokens as all tokens are treated equally during training. In this work, we introduce a Reinforcement Iterative Sequence Editing (RISE) framework that optimizes the minimum Levenshtein distance (MLD) through explicit editing actions. RISE is able to pay attention to tokens that are related to conversational characteristics. To train RISE, we devise an Iterative Reinforce Training (IRT) algorithm with a Dynamic Programming based Sampling (DPS) process to improve exploration. Experimental results on two benchmark datasets show that RISE significantly outperforms state-of-the-art methods and generalizes well on unseen data.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑