Multi-domain Dialogue State Tracking as Dynamic Knowledge Graph Enhanced Question Answering

By Li Zhou, Kevin Small. 2019

92 citations recorded by the source corpus.

Multi-domain dialogue state tracking (DST) is a critical component for conversational AI systems. The domain ontology (i.e., specification of domains, slots, and values) of a conversational AI system is generally incomplete, making the capability for DST models to generalize to new slots, values, and domains during inference imperative. In this paper, we propose to model multi-domain DST as a question answering problem, referred to as Dialogue State Tracking via Question Answering (DSTQA). Within DSTQA, each turn generates a question asking for the value of a (domain, slot) pair, thus making it naturally extensible to unseen domains, slots, and values. Additionally, we use a dynamically-evolving knowledge graph to explicitly learn relationships between (domain, slot) pairs. Our model has a 5.80% and 12.21% relative improvement over the current state-of-the-art model on MultiWOZ 2.0 and MultiWOZ 2.1 datasets, respectively. Additionally, our model consistently outperforms the state-of-the-art model in domain adaptation settings. (Code is released at this https URL )

Subfields: Artificial Intelligence, Natural Language Processing

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

In Natural Language Processing

Citations in the corpus

A Simple Language Model for Task-Oriented Dialogue (2020, background): “DSTQA also accounts for label variations that would have originally been considered incorrect.”
Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue StateTracking (2021, methodology): “To address this issue, several methods (Wu et al., 2019; Zhou and Small, 2019) have proposed for transferring prior knowledge of existing domains to new ones.”
MultiWOZ 2.2 : A Dialogue Dataset with Additional Annotation Corrections and State Tracking Baselines (2020, background): “…the locations in the user and system utterances where slot values have been mentioned, to make the system efﬁcient and generalizable to new slot values (Rastogi et al., 2017; Wu et al., 2019; Zhang et al., 2019; Rastogi et al., 2019; Xu and Hu, 2018; Zhou and Small, 2019; Gao et al., 2019).”
MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems (2020, unknown): “…al., 2019), SST (Chen et al., 2020), TOD-BERT (Wu et al., 2020), and DST-Picklist (Zhang et al., 2019a); the latter includes Neural Reading (Gao et al., 2019), TRADE (Wu et al., 2019a), COMER (Ren et al., 2019), SOM-DST (Kim et al., 2019), DSTQA (Zhou and Small, 2019), and NADST (Le et al., 2020).”
Dialogue State Tracking with a Language Model using Schema-Driven Prompting (2021, result): “In summary, there are four types of errors: (i) The most common error type is annotation error in which the model prediction is actually correct, which is similar to the findings of (Zhou and Small, 2019).”
Find or Classify? Dual Strategy for Slot-Value Predictions on Multi-Domain Dialog State Tracking (2019, background): “To mitigate the above issues, recently, (Zhou and Small, 2019) introduced a question asking model to generate questions asking for values of eachdomain slot pair and a dynamic knowledge graph to learn relationships between the (domain, slot) pairs.”
Zero-Shot Transfer Learning with Synthesized Data for Multi-Domain Dialogue State Tracking (2020, methodology): “The MultiWOZ dataset still has significant inconsistencies (Zhou and Small, 2019) despite having been constructed through multiple rounds of annotations (Budzianowski et al.”
Recent Advances in Natural Language Processing via Large Pre-trained Language Models: A Survey (2021, result): “The latter setting was also investigated by Zhou and Small [223] who further improved the results.”