- Abstract: Spoken language understanding (SLU) is a critical component in building dialogue systems. When building models for novel natural language domains, a major challenge is the lack of data in the new domains, no matter whether the data is annotated or not. Recognizing and annotating ``intent'' and ``slot'' of natural languages is a time-consuming process. Therefore, spoken language understanding in low resource domains remains a crucial problem to address. In this paper, we address this problem by proposing a transfer-learning method, whereby a SLU model is transferred to a novel but data-poor domain via a deep neural network framework. We also introduce meta-learning in our work to bridge the semantic relations between seen and unseen data, allowing new intents to be recognized and new slots to be filled with much lower new training effort. We show the performance improvement with extensive experimental results for spoken language understanding in low resource domains. We show that our method can also handle novel intent recognition and slot-filling tasks. Our methodology provides a feasible solution for alleviating data shortages in spoken language understanding.
- Keywords: transfer learning, semantic representation, spoken language understanding
- TL;DR: v3