A Word and Local Feature Aware Network for Chinese Spoken Language Understanding

Chinese SLU suffers from unclear word boundaries. Previous works were either missing the word information or afflicted by word segmentation errors. In this paper, we propose a novel Word and Local feature Aware Network (WLAN), which incorporates both word information and local features for Chinese SLU while avoiding word segmentation. In addition, in our knowledge we first time use the potential slots likely to co-occur with the predicted intent as specific guidance. Experimental results on two Chinese SLU datasets show that our model gets very competitive performance.