2020/10/24 by Yan Zeng, Zeng, Yan, Jian‐Yun Nie +1
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Service-Oriented Architecture and Web Services #Speech and dialogue systems #Topic Modeling
paper · pdf · doi:10.48550/arxiv.2010.14061
openalex publication_date 2020/10/24 · openalex created_date 2021/04/13 · openalex updated_date 2026/07/28
We investigate the problem of multi-domain Dialogue State Tracking (DST) with open vocabulary. Existing approaches exploit BERT encoder and copy-based RNN decoder, where the encoder predicts the state operation, and the decoder generates new slot values. However, in such a stacked encoder-decoder structure, the operation prediction objective only affects the BERT encoder and the value generation objective mainly affects the RNN decoder. In this paper, we propose a purely Transformer-based framework, where a single BERT works as both the encoder and the decoder. In so doing, the operation prediction objective and the value generation objective can jointly optimize this BERT for DST. At the decoding step, we re-use the hidden states of the encoder in the self-attention mechanism of the corresponding decoder layers to construct a flat encoder-decoder architecture for effective parameter updating. Experimental results show that our approach substantially outperforms the existing state-of-the-art framework, and it also achieves very competitive performance to the best ontology-based approaches.