论文标题
跨语言语言理解与正规表示
Cross-lingual Spoken Language Understanding with Regularized Representation Alignment
论文作者
论文摘要
尽管目前用于口语理解系统的跨语性模型有令人鼓舞的结果，但它们仍然遭受源和目标语言之间不完善的跨语性表示对准，这使得绩效次优最佳。为了应对这个问题，我们提出了一种正则化方法，以进一步使单词级别和句子级别的表示跨语言不带任何外部资源。首先，我们根据用户的话语根据其相应的标签进行定期表示。其次，我们通过利用对抗性训练来解开潜在变量来正规化潜在变量模型（Liu等，2019）。跨语言口语理解任务的实验表明，我们的模型在几次和零拍的场景中都优于当前最新方法，而我们的模型在几个射击设置上进行了培训，只有3 \％的目标语言培训数据，通过所有培训数据实现了可比较的绩效，可以实现可比较的绩效。
Despite the promising results of current cross-lingual models for spoken language understanding systems, they still suffer from imperfect cross-lingual representation alignments between the source and target languages, which makes the performance sub-optimal. To cope with this issue, we propose a regularization approach to further align word-level and sentence-level representations across languages without any external resource. First, we regularize the representation of user utterances based on their corresponding labels. Second, we regularize the latent variable model (Liu et al., 2019) by leveraging adversarial training to disentangle the latent variables. Experiments on the cross-lingual spoken language understanding task show that our model outperforms current state-of-the-art methods in both few-shot and zero-shot scenarios, and our model, trained on a few-shot setting with only 3\% of the target language training data, achieves comparable performance to the supervised training with all the training data.
