提出两阶段编辑操作框架，提升对话中省略句重写效果
Two-stage Incomplete Utterance Rewriting on Editing Operation
- 先生成编辑操作，再基于操作重写不完整对话
- 在三个数据集上显著优于现有最佳模型
- 用对抗扰动缓解训练与推理不一致问题，适合对话系统研究者
以往的不完整话语重写（IUR）工作主要依赖对话上下文生成重写语句，忽略了对话中常见的指代和省略现象。为此，我们提出一种名为TEO（两阶段编辑操作方法）的新框架，第一阶段生成编辑操作，第二阶段利用生成的编辑操作和对话上下文重写不完整话语。此外，提出对抗性扰动策略，缓解第二阶段因训练与推理不一致导致的级联错误和暴露偏差。在三个IUR数据集上的实验结果表明，TEO显著优于当前最优模型。
原文摘要 · Abstract (English)
Previous work on Incomplete Utterance Rewriting (IUR) has primarily focused on generating rewritten utterances based solely on dialogue context, ignoring the widespread phenomenon of coreference and ellipsis in dialogues. To address this issue, we propose a novel framework called TEO (\emph{Two-stage approach on Editing Operation}) for IUR, in which the first stage generates editing operations and the second stage rewrites incomplete utterances utilizing the generated editing operations and the dialogue context. Furthermore, an adversarial perturbation strategy is proposed to mitigate cascading errors and exposure bias caused by the inconsistency between training and inference in the second stage. Experimental results on three IUR datasets show that our TEO outperforms the SOTA models significantly.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。