Sequence-to-Sequence Data Augmentation for Dialogue Language Understanding

Proceedings of the 27th International Conference on Computational Linguistics, pages 1234–1245 Santa Fe, New Mexico, USA, August 20-26, 2018. 1234 Sequence-to-Sequence Data Augmentation for Dialogue Language Understanding Yutai Hou, Yijia Liu, Wanxiang Che*, Ting Liu Research Center for Social Computing and Information Retrieval Harbin Institute of Technology, China {ythou, yjliu, car, tliu}@ir.hit.edu.cn Abstract In this paper, we study the problem of data augmentation for language understanding in task- oriented dialogue system. In contrast to previous work which augments an utterance without considering its relation with other utterances, we propose a sequence-to-sequence generation based data augmentation framework that leverages one utterance’s same semantic alternatives in the training data. A novel diversity rank is incorporated into the utterance representation to make the model produce diverse utterances and these diversely augmented utterances help to improve the language understanding module. Experimental results on the Airline Travel Information System dataset and a newly created semantic frame annotation on Stanford Multi-turn, Multi- domain Dialogue Dataset show that our framework achieves significant improvements of 6.38 and 10.04 F-scores respectively when only a training set of hundreds utterances is represented. Case studies also confirm that our method generates diverse utterances. Title and Abstract in Chinese 对话语义理解的序列到序列数据增强 在本文中，我们研究了面向任务的对话系统中语言理解模块的数据增强问题。相比之前 的工作在生成新语句时不考虑语句间关系，我们利用训练数据中与一个语句具有相同语 义的其他句子，提出了基于序列到序列生成的数据增强框架。我们创新地将多样性等级 结合到话语表示中以使模型产生多样化的语句数据，而这些多样化的新语句有助于改善 语言理解模块。在航空旅行信息系统数据集以及一个新标注的斯坦福多轮多域对话数 据集上的实验结果表明，当训练集仅包含数百句语料时，我们的框架在F值上分别实现 了6.38和10.04的显着提升。案例研究也证实我们的方法能够产生多样化的话语。 1 Introduction Language understanding (LU) is the initial and essential component in the task-oriented dialogue system pipeline (Young et al., 2013). One challenge in building robust LU is to handle myriad ways in which users express demands. This challenge becomes more serious when switching to a new domain whose large-scale labeled data is usually unreachable. Insufficiency in training data makes LU vulnerable to unseen utterances which are syntactically different but semantically related to the existing training data, and further harms the whole task-oriented dialogue system pipeline. Data augmentation, which enlarges the size of training data in machine learning systems, is an effec- tive solution to the data insufficiency problem. Success has been achieved with data augmentation on a wide range of problems including computer vision (Krizhevsky et al., 2012), speech recognition (Han- nun et al., 2014), text classification (Zhang et al., 2015), and question answering (Fader et al., 2013). However, its application in the task-oriented dialogue system is less studied. Kurata et al. (2016a) pre- sented the only work we know that tried to augment data for LU. In their paper, an encoder-decoder is This work is licenced under a Creative Commons Attribution 4.0 International Licence. Licence details: http:// creativecommons.org/licenses/by/4.0/ * Email corresponding. 1235 learned to reconstruct the utterances in the training data. During the augmenting process, the encoder’s output hidden states are randomly perturbed to yield different utterances. The work of Kurata et al. (2016a) augments one single utterance by adding noise without considering its relation with other utterances. Besides theirs, there are also works which explicitly consider the paraphrasing relations between instances that share the same output. These works achieve improvements on tasks like text classification and question answering. Paraphrasing techniques including word-level substitution (Zhang et al., 2015; Wang and Yang, 2015), hand-crafted …

Content truncated to 500 words