Dialogue State Tracking with Explicit Slot Connection Modeling

Ouyang, Yawen; Chen, Moxin; Dai, Xinyu; Zhao, Yinggong; Huang, Shujian; Chen, Jiajun

doi:10.18653/v1/2020.acl-main.5

Cited by 36 publications

(34 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous work has addressed sharing information between slots either by explicitly copying values (Ouyang et al, 2020;Heck et al, 2020) or by sharing embeddings Zhou and Small, 2019;. Beyond copying and sharing, as we note in Sec.…”

Section: Related Workmentioning

confidence: 94%

Knowledge-Aware Graph-Enhanced GPT-2 for Dialogue State Tracking

Lin¹,

Tseng²,

Byrne³

2021

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

Dialogue State Tracking is central to multidomain task-oriented dialogue systems, responsible for extracting information from user utterances. We present a novel hybrid architecture that augments GPT-2 with representations derived from Graph Attention Networks in such a way to allow causal, sequential prediction of slot values. The model architecture captures inter-slot relationships and dependencies across domains that otherwise can be lost in sequential prediction. We report improvements in state tracking performance in Mul-tiWOZ 2.0 against a strong GPT-2 baseline and investigate a simplified sparse training scenario in which DST models are trained only on session-level annotations but evaluated at the turn level. We further report detailed analyses to demonstrate the effectiveness of graph models in DST by showing that the proposed graph modules capture inter-slot dependencies and improve the predictions of values that are common to multiple domains.

show abstract

Section: Related Workmentioning

confidence: 94%

Knowledge-Aware Graph-Enhanced GPT-2 for Dialogue State Tracking

Lin¹,

Tseng²,

Byrne³

2021

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

show abstract

“…At each step, the new data (D i ) can contain one or multiple new domains. In addition, inspired by other lifelong learning work (Lopez-Paz and Ranzato, 2017;Zenke et al, 2017) across the same multiple domains as data of a special domain, since these cross-domain dialogues usually contain specific expressions that distinguish them from other dialogues, such as domain transformation and slot reference (Ouyang et al, 2020;Hu et al, 2020) ). The updated model should still perform well on all previous domains.…”

Section: Task Formulationmentioning

confidence: 99%

Domain-Lifelong Learning for Dialogue State Tracking via Knowledge Preservation Networks

Liu¹,

Cao²,

Cao³

et al. 2021

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

Dialogue state tracking (DST), which estimates user goals given a dialogue context, is an essential component of task-oriented dialogue systems. Conventional DST models are usually trained offline, which requires a fixed dataset prepared in advance. This paradigm is often impractical in real-world applications since online dialogue systems usually involve continually emerging new data and domains. Therefore, this paper explores Domain-Lifelong Learning for Dialogue State Tracking (DLL-DST), which aims to continually train a DST model on new data to learn incessantly emerging new domains while avoiding catastrophically forgetting old learned domains. To this end, we propose a novel domainlifelong learning method, called Knowledge Preservation Networks (KPN), which consists of multi-prototype enhanced retrospection and multi-strategy knowledge distillation, to solve the problems of expression diversity and combinatorial explosion in the DLL-DST task. Experimental results show that KPN effectively alleviates catastrophic forgetting and outperforms previous state-of-the-art lifelong learning methods by 4.25% and 8.27% of whole joint goal accuracy on the MultiWOZ benchmark and the SGD benchmark, respectively.

show abstract

“…It involves 7 domains and 18 slots, which form 35 domain-slot pairs. We conducted evaluations on the latest MultiWOZ 2.1 dataset [15], which 35.57 -DST Reader [17] 39.41 36.4 COMER [9] 45.72 -TRADE [8] 48.62 45.6 NADST [18] 50.52 49.0 SAS [19] 51.03 -DST-SC [20] 52.24 49.6 PRO-DST (Ours) 51.48 49.9…”

Section: Datasetsmentioning

confidence: 99%

Progressive Dialogue State Tracking for Multi-Domain Dialogue Systems

Wang

Liu

2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

There are two critical observations in multi-domain dialogue state tracking (DST) ignored in most existing work. First, the number of triples (domain-slot-value) in dialogue states generally increases with the growth of dialogue turns. Second, although dialogue states are accumulating, the difference between two adjacent turns is steadily minor. To model the two observations, we propose to divide the task into two successive procedures: progressive domain-slot tracking and shrunk value prediction. Specifically, domain-slot pairs are first modeled in a multi-level structure that can be predicted progressively based on previous turns. Then, we employ a generative approach to producing dialogue values for the predicted, rather than for all possible, domain-slot pairs. This divide-and-conquer approach not only enables parallelization for predicting domain-slot pairs, but also significantly reduces the number of domain-slot candidates for value prediction. Experimental results on the MultiWOZ datasets confirm that our methodology (PRO-DST) achieves very favorable improvement over existing methods.

show abstract

Dialogue State Tracking with Explicit Slot Connection Modeling

Cited by 36 publications

References 18 publications

Knowledge-Aware Graph-Enhanced GPT-2 for Dialogue State Tracking

Knowledge-Aware Graph-Enhanced GPT-2 for Dialogue State Tracking

Domain-Lifelong Learning for Dialogue State Tracking via Knowledge Preservation Networks

Progressive Dialogue State Tracking for Multi-Domain Dialogue Systems

Contact Info

Product

Resources

About