SUMBT: Slot-Utterance Matching for Universal and Scalable Belief Tracking

By Hwaran Lee, Jinsik Lee, Tae-Yoon Kim. 2019

177 citations recorded by the source corpus.

In goal-oriented dialog systems, belief trackers estimate the probability distribution of slot-values at every dialog turn. Previous neural approaches have modeled domain- and slot-dependent belief trackers, and have difficulty in adding new slot-values, resulting in lack of flexibility of domain ontology configurations. In this paper, we propose a new approach to universal and scalable belief tracker, called slot-utterance matching belief tracker (SUMBT). The model learns the relations between domain-slot-types and slot-values appearing in utterances through attention mechanisms based on contextual semantic vectors. Furthermore, the model predicts slot-value labels in a non-parametric way. From our experiments on two dialog corpora, WOZ 2.0 and MultiWOZ, the proposed model showed performance improvement in comparison with slot-dependent methods and achieved the state-of-the-art joint accuracy.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Continual Prompt Tuning for Dialog State Tracking (2022, methodology): “Traditional ontology-based classification methods (Mrkšić et al., 2017; Lee et al., 2019) require access to all candidate values.”
Uncertainty Measures in Neural Belief Tracking and the Effects on Dialogue Policy Performance (2021, methodology): “We base our tracker on the slot-utterance matching belief tracker (SUMBT) (Lee et al., 2019), but we make two important changes.”
End-to-End Neural Pipeline for Goal-Oriented Dialogue Systems using GPT-2 (2020, methodology): “ConvLab contains implementations of the state-of-the-art models of NLU, DST, POL, NLG (Kim et al., 2017; Lee et al., 2019b; Ramadan et al., 2018; Wu et al., 2019; Wen et al., 2015, 2017; Budzianowski et al., 2018) and an end-to-end neural model for dialogue systems (Lei et al., 2018; Madotto et…”
Multi-domain Dialogue State Tracking as Dynamic Knowledge Graph Enhanced Question Answering (2019, methodology): “SUMBT (Lee et al., 2019) finetunes a pre-trained BERT model (Devlin et al.”
Zero-Shot Transfer Learning with Synthesized Data for Multi-Domain Dialogue State Tracking (2020, methodology): “• We show that our approach improves the accuracy for TRADE (Wu et al., 2019), an RNN-based model, and SUMBT (Lee et al., 2019), a BERT-based model (Devlin et al., 2019), suggesting that our technique is independent of the speciﬁc model used.”
Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialogue State Tracking (2021, unknown): “0 GLAD (Zhong et al., 2018) 35.57% ∗∗ 88.1 ± 0.4% SUMBT (Lee et al., 2019) 46.65% ∗∗ 91.0 ± 1.0% DST-picklist (Zhang et al., 2019) 53.30% – Trippy (Heck et al., 2020) 55.29 ± 0.28% 92.7 ± 0.2% SimpleTOD (Hosseini-Asletal.,2020) 55.72% – CHAN (Shan et al., 2020) 58 the maximum length is 256.”
MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems (2020, methodology): “…outperform the DAMD (Zhang et al., 2019b), MD-Sequicity (Lei et al., 2018) (Eric et al., 2019) 40.20 38.00 HyST (Goel et al., 2019) † 44.24 - SUMBT (Lee et al., 2019) † 46.65 - TOD-BERT (Wu et al., 2020) - 48.00 DST-Picklist (Zhang et al., 2019a) - 53.30 SST (Chen et al., 2020) 51.17 55.23 Neural…”
Schema-Guided Multi-Domain Dialogue State Tracking with Graph Attention Neural Networks (2020, background): “…GCE (Nouri and Hosseini-Asl 2018), a global-conditioned encoder; HJST (Eric et al. 2019) and FJST (Eric et al. 2019), which refer to the Flat Joint State Tracker and the Hierarchical Joint State Tracker respectively. and SUMBT (Lee, Lee, and Kim 2019), a slot-utterance matching belief tracker.”
Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue StateTracking (2021, methodology): “Slot-utterance matching belief tracker (Lee et al., 2019) based on the language model BERT (Devlin et al., 2018).”
Find or Classify? Dual Strategy for Slot-Value Predictions on Multi-Domain Dialog State Tracking (2019, methodology): “Similar to (Lee et al., 2019; Chen et al., 2020), It assumes a full ontology is available Models Joint Accuracy”
ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems (2020, methodology): “ConvLab (Lee et al., 2019b) is the first toolkit that provides various powerful models for all dialogue components and allows researchers to quickly assemble a complete dialogue system (using a set of recipes).”
TripPy: A Triple Copy Strategy for Value Independent Neural Dialog State Tracking (2020, methodology): “We also differ from approaches like Lee et al. (2019) since we do not employ recurrence.”