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 2012.14535cs.CL
收藏

基于序列标记的鲁棒对话话语重写

Robust Dialogue Utterance Rewriting as Sequence Tagging

Florida State University(佛罗里达州立大学);Tencent AI Lab(腾讯人工智能实验室);The Chinese University of Hong Kong(香港中文大学)

Jie Hao, Linfeng Song, Liwei Wang, Kun Xu, Zhaopeng Tu, Dong Yu

摘要:

对话改写的任务是从对话语境中复制缺失的内容,从而重构最新的对话话语。到目前为止,用于该任务的现有模型遭受鲁棒性问题,即,在不同的域上进行测试时,性能会急剧下降。我们通过提出一种新的基于序列标记的模型来解决这个鲁棒性问题,从而显著减少了搜索空间,但仍然很好地覆盖了这项任务的核心。作为大多数用于文本生成的标记模型的共同问题,模型的输出可能缺乏流畅性。为了缓解这个问题,我们在REINFORCE框架下注入来自BLEU或GPT-2的丢失信号。实验表明,我们的模型在域转移的当前国家的最先进的系统有很大的改进。

英文摘要:

The task of dialogue rewriting aims to reconstruct the latest dialogue utterance by copying the missing content from the dialogue context. Until now, the existing models for this task suffer from the robustness issue, i.e., performances drop dramatically when testing on a different domain. We address this robustness issue by proposing a novel sequence-tagging-based model so that the search space is significantly reduced, yet the core of this task is still well covered. As a common issue of most tagging models for text generation, the model's outputs may lack fluency. To alleviate this issue, we inject the loss signal from BLEU or GPT-2 under a REINFORCE framework. Experiments show huge improvements of our model over the current state-of-the-art systems on domain transfer.

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。

↑