Paper ID | SS-5.3 | ||
Paper Title | INJECTING WORD INFORMATION WITH MULTI-LEVEL WORD ADAPTER FOR CHINESE SPOKEN LANGUAGE UNDERSTANDING | ||
Authors | Dechuan Teng, Libo Qin, Wanxiang Che, Sendong Zhao, Ting Liu, Harbin Institute of Technology, China | ||
Session | SS-5: Domain Adaptation for Multimedia Signal Processing | ||
Location | Gather.Town | ||
Session Time: | Wednesday, 09 June, 13:00 - 13:45 | ||
Presentation Time: | Wednesday, 09 June, 13:00 - 13:45 | ||
Presentation | Poster | ||
Topic | Special Sessions: Domain Adaptation for Multimedia Signal Processing | ||
IEEE Xplore Open Preview | Click here to view in IEEE Xplore | ||
Abstract | In this paper, we improve Chinese spoken language understanding (SLU) by injecting word information. Previous studies on Chinese SLU do not consider the word information, failing to detect word boundaries that are beneficial for intent detection and slot filling. To address this issue, we propose a multi-level word adapter to inject word information for Chinese SLU, which consists of (1) sentence-level word adapter, which directly fuses the sentence representations of the word information and character information to perform intent detection and (2) character-level word adapter, which is applied at each character for selectively controlling weights on word information as well as character information. Experimental results on two Chinese SLU datasets show that our model can capture useful word information and achieve state-of-the-art performance. |