Jointly Optimizing State Operation Prediction and Value Generation for Dialogue State Tracking

24 Oct 2020  ·  Yan Zeng, Jian-Yun Nie ·

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.

PDF Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Multi-domain Dialogue State Tracking MULTIWOZ 2.0 Transformer-DST Joint Acc 54.64 # 2
Multi-domain Dialogue State Tracking MULTIWOZ 2.1 Transformer-DST Joint Acc 55.35 # 10

Methods