基于编辑操作引导与话语增强的不完整话语改写
Incomplete Utterance Rewriting with Editing Operation Guidance and Utterance Augmentation
AI总结：
针对不完整话语改写中生成冗余无关内容、训练数据不足的问题，提出带编辑操作引导和标记级异构图的EO-IUR框架及二维话语增强策略，在三类数据集上性能超越现有SOTA模型。
摘要：
尽管当前流行的不完整话语改写（Incomplete Utterance Rewriting, IUR）生成方法能够生成连贯的话语，但由于无法聚焦对话上下文中的关键标记，它们往往会导致改写后的话语包含无关且冗余的标记。此外，训练数据集规模有限也会导致IUR模型训练不充分。为解决第一个问题，我们提出了多任务学习框架EO-IUR（编辑操作引导的不完整话语改写），该框架引入由序列标注模块生成的编辑操作标签，引导生成模型聚焦关键标记；此外，我们还引入了标记级异构图来表示对话。为解决第二个问题，我们提出了二维话语增强策略，即基于编辑操作的不完整话语增强和基于大语言模型（LLM）的历史话语增强。在三个数据集上的实验结果表明，我们的EO-IUR在开放域和任务型对话中均优于此前的最优（SOTA）基线模型。代码将发布于https://github.com/Dewset/EO-IUR。
英文摘要：
Although existing fashionable generation methods on Incomplete Utterance Rewriting (IUR) can generate coherent utterances, they often result in the inclusion of irrelevant and redundant tokens in rewritten utterances due to their inability to focus on critical tokens in dialogue context. Furthermore, the limited size of the training datasets also contributes to the insufficient training of the IUR model. To address the first issue, we propose a multi-task learning framework EO-IUR (Editing Operation-guided Incomplete Utterance Rewriting) that introduces the editing operation labels generated by sequence labeling module to guide generation model to focus on critical tokens. Furthermore, we introduce a token-level heterogeneous graph to represent dialogues. To address the second issue, we propose a two-dimensional utterance augmentation strategy, namely editing operation-based incomplete utterance augmentation and LLM-based historical utterance augmentation. The experimental results on three datasets demonstrate that our EO-IUR outperforms previous state-of-the-art (SOTA) baselines in both open-domain and task-oriented dialogue. The code will be available at https://github.com/Dewset/EO-IUR.
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。
