声音自然：对话系统中的内容改写
Sound Natural: Content Rephrasing in Dialog Systems
摘要：
我们引入了一项重新措辞的新任务，以获得更自然的虚拟助理。目前，虚拟助理在意图槽标记的范例中工作，并且槽值直接按原样传递到执行引擎。但是，在某些情况下，这种设置会失败，例如当用户给出的查询需要在重复之前进行更改或将其发送给另一个用户时。例如，对于像“问我的妻子，如果她可以接孩子”或“提醒我吃药”这样的查询，我们需要将内容改写为“你能接孩子吗”和“吃药”在本文中，我们研究了消息传递作为用例的改写问题，并发布了3000对原始查询和改写查询的数据集。我们表明，BART，一个预先训练的基于transformers的掩蔽语言模型与自回归解码，是一个强大的基线的任务，并通过添加一个复制指针和复制损失，它显示改进。我们分析了不同的权衡基于BART和基于LSTM的seq2seq模型，并提出了一个蒸馏基于LSTM的seq2seq作为最佳的实用模型。
英文摘要：
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.
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。
