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 2208.07097cs.CLcs.AI
收藏

以应答选择为辅助任务的面向任务的高效对话系统

Efficient Task-Oriented Dialogue Systems with Response Selection as an Auxiliary Task

High School of Mathematics(数学高中);Obecto Ltd.(Obecto有限公司)

Radostin Cholakov, Todor Kolev

摘要:

在面向任务的对话系统中采用预先训练好的语言模型,大大提高了系统的文本生成能力。然而,由于大量的可训练参数,这些架构使用起来很慢,有时可能无法生成不同的响应。为了解决这些局限性,我们提出了两个模型与辅助任务的反应选择-(1)区分干扰物从地面真实反应和(2)区分合成反应从地面真实标签。他们在MultiWOZ 2.1数据集上获得了最先进的结果,综合得分为107.5和108.3,并且优于基线,参数增加了三倍。我们发布了可复制的代码和检查点,并讨论了将辅助任务应用于基于T5的架构的效果。

英文摘要:

The adoption of pre-trained language models in task-oriented dialogue systems has resulted in significant enhancements of their text generation abilities. However, these architectures are slow to use because of the large number of trainable parameters and can sometimes fail to generate diverse responses. To address these limitations, we propose two models with auxiliary tasks for response selection - (1) distinguishing distractors from ground truth responses and (2) distinguishing synthetic responses from ground truth labels. They achieve state-of-the-art results on the MultiWOZ 2.1 dataset with combined scores of 107.5 and 108.3 and outperform a baseline with three times more parameters. We publish reproducible code and checkpoints and discuss the effects of applying auxiliary tasks to T5-based architectures.

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。

↑