A Sequence-to-Sequence Approach to Dialogue State Tracking

ACL 2021  ·  Yue Feng, Yang Wang, Hang Li ·

This paper is concerned with dialogue state tracking (DST) in a task-oriented dialogue system. Building a DST module that is highly effective is still a challenging issue, although significant progresses have been made recently. This paper proposes a new approach to dialogue state tracking, referred to as Seq2Seq-DU, which formalizes DST as a sequence-to-sequence problem. Seq2Seq-DU employs two BERT-based encoders to respectively encode the utterances in the dialogue and the descriptions of schemas, an attender to calculate attentions between the utterance embeddings and the schema embeddings, and a decoder to generate pointers to represent the current state of dialogue. Seq2Seq-DU has the following advantages. It can jointly model intents, slots, and slot values; it can leverage the rich representations of utterances and schemas based on BERT; it can effectively deal with categorical and non-categorical slots, and unseen schemas. In addition, Seq2Seq-DU can also be used in the NLU (natural language understanding) module of a dialogue system. Experimental results on benchmark datasets in different settings (SGD, MultiWOZ2.2, MultiWOZ2.1, WOZ2.0, DSTC2, M2M, SNIPS, and ATIS) show that Seq2Seq-DU outperforms the existing methods.

PDF Abstract ACL 2021 PDF ACL 2021 Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Multi-domain Dialogue State Tracking MULTIWOZ 2.1 Seq2Seq-DU Joint Acc 56.1 # 6
Multi-domain Dialogue State Tracking MULTIWOZ 2.2 Seq2Seq-DU Joint Acc 54.4 # 4
Dialogue State Tracking Second dialogue state tracking challenge Seq2Seq-DU-w/oSchema Joint 85 # 1
Classification SGD SGD_ss F1 (Seqeval) 2020 # 1
Multi-domain Dialogue State Tracking SGD Seq2Seq-DU Joint 30.1 # 1
Dialogue State Tracking Wizard-of-Oz Seq2Seq-DU-w/oSchema Joint 91.2 # 2

Methods


No methods listed for this paper. Add relevant methods here