论文标题
声音自然：对话系统中的内容重新设计
Sound Natural: Content Rephrasing in Dialog Systems
论文作者
论文摘要
我们介绍了为更自然的虚拟助手改造的新任务。当前，虚拟助手在意图插槽标记的范式中工作，插槽值直接传递给了执行引擎。但是，在某些情况下，当用户给出的查询重复或将其发送给其他用户时，此设置在某些情况下（例如消息传递）失败。例如，要查询诸如“问我妻子是否可以接孩子”或“提醒我服用药丸”之类的问题，我们需要在本文中重新调整内容，以“您可以接孩子吧”并“服用您的药丸”，我们研究将消息用作用途的问题，并释放出3000对原始Query Query Query和Rephrhrhrhrhrhrhr的数据集。我们表明，BART是一种基于自动回报解码的预先训练的基于变形金刚的掩盖语言模型，是该任务的强大基准，并通过在其上添加复制定位器和复制损失来显示改进。我们分析了基于BART和基于LSTM的SEQ2SEQ模型的不同权衡，并提出了基于LSTM的SEQ2SEQ作为最佳实用模型。
We introduce a new task of rephrasing for a more natural virtual assistant. Currently, virtual assistants work in the paradigm of intent slot tagging and the slot values are directly passed as-is to the execution engine. However, this setup fails in some scenarios such as messaging when the query given by the user needs to be changed before repeating it or sending it to another user. For example, for queries like 'ask my wife if she can pick up the kids' or 'remind me to take my pills', we need to rephrase the content to 'can you pick up the kids' and 'take your pills' In this paper, we study the problem of rephrasing with messaging as a use case and release a dataset of 3000 pairs of original query and rephrased query. We show that BART, a pre-trained transformers-based masked language model with auto-regressive decoding, is a strong baseline for the task, and show improvements by adding a copy-pointer and copy loss to it. We analyze different tradeoffs of BART-based and LSTM-based seq2seq models, and propose a distilled LSTM-based seq2seq as the best practical model.
