From General to Specific: Leveraging Named Entity Recognition for Slot Filling in Conversational Language Understanding.

Slot filling techniques are often adopted in language understanding components for task-oriented dialogue systems. In recent approaches, neural models for slot filling are trained on domainspecific datasets, making it difficult porting to similar domains when few or no training data are available. In this paper we use multi-task learning to leverage general knowledge of a task, namely Named Entity Recognition (NER), to improve slot filling performance on a semantically similar domain-specific task. Our experiments show that, for some datasets, transfer learning from NER can achieve competitive performance compared with the state-of-the-art and can also help slot filling in low resource scenarios