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 2207.00929cs.CL
收藏

用适当的重复词生成重复

Generating Repetitions with Appropriate Repeated Words

Tokyo Institute of Technology(东京工业大学)

Toshiki Kawamoto, Hidetaka Kamigaito, Kotaro Funakoshi, Manabu Okumura

摘要:

重复是在对话中重复前一个说话者的话语的反应。语言学研究表明,重复是交际中建立信任的重要手段。在这项工作中,我们专注于重复生成。据我们所知,这是第一个解决重复生成的神经方法。我们提出了加权标签平滑,一种平滑方法,用于明确学习哪些单词在微调过程中重复,以及一种重复评分方法,可以在解码过程中输出更合适的重复。我们进行了自动和人工评估,包括将这些方法应用于预训练的语言模型T5以生成重复。实验结果表明,我们的方法优于基线在这两个评估。

英文摘要:

A repetition is a response that repeats words in the previous speaker's utterance in a dialogue. Repetitions are essential in communication to build trust with others, as investigated in linguistic studies. In this work, we focus on repetition generation. To the best of our knowledge, this is the first neural approach to address repetition generation. We propose Weighted Label Smoothing, a smoothing method for explicitly learning which words to repeat during fine-tuning, and a repetition scoring method that can output more appropriate repetitions during decoding. We conducted automatic and human evaluations involving applying these methods to the pre-trained language model T5 for generating repetitions. The experimental results indicate that our methods outperformed baselines in both evaluations.

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。

↑