Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems

Wu, Chien-Sheng; Madotto, Andrea; Hosseini-Asl, Ehsan; Xiong, Caiming; Socher, Richard; Fung, Pascale

doi:10.48550/arxiv.1905.08743

Cited by 31 publications

(25 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As noted by Razumovskaia et al (2021), there are two main designs for ToD systems: modular ToD systems and end-to-end ToD systems. In modular ToD systems, dialogue state tracking is an important component that parses the user's goal from the dialogue utterances (Wu et al, 2019b;Heck et al, 2020;Hosseini-Asl et al, 2020;Lin et al, 2020b). Among these popular models, Transformer-DST (Zeng and Nie, 2020) is one of the state-of-the-art models on both MultiWoZ 2.0 and MultiWoZ 2.1 4 .…”

Section: Multilingual Tod Systemmentioning

confidence: 99%

GlobalWoZ: Globalizing MultiWoZ to Develop Multilingual Task-Oriented Dialogue Systems

Ding¹,

Hu²,

Aljunied³

et al. 2021

Preprint

View full text Add to dashboard Cite

Much recent progress in task-oriented dialogue (ToD) systems has been driven by available annotation data across multiple domains for training. Over the last few years, there has been a move towards data curation for multilingual ToD systems that are applicable to serve people speaking different languages. However, existing multilingual ToD datasets either have a limited coverage of languages due to the high cost of data curation, or ignore the fact that dialogue entities barely exist in countries speaking these languages. To tackle these limitations, we introduce a novel data curation method that generates GlobalWoZ -a largescale multilingual ToD dataset globalized from an English ToD dataset for three unexplored use cases. Our method is based on translating dialogue templates and filling them with local entities in the target-language countries. We release our dataset as well as a set of strong baselines to encourage research on learning multilingual ToD systems for real use cases.

show abstract

Section: Multilingual Tod Systemmentioning

confidence: 99%

GlobalWoZ: Globalizing MultiWoZ to Develop Multilingual Task-Oriented Dialogue Systems

Ding¹,

Hu²,

Aljunied³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The performance of NBT is much better than previous DST methods. Inspired by this seminal work, a lot of neural DST approaches based on long short-term memory (LSTM) network [34,[40][41][42]59] and bidirectional gated recurrent unit (BiGRU) network [22,31,35,39,55,57] have been proposed for further improvements. These methods define DST as either a classification problem or a generation problem.…”

Section: Related Workmentioning

confidence: 99%

“…According to [11], about 32% of the state annotations have been corrected in MultiWOZ 2.1. Since hospital and police are not included in the validation set and test set, following previous works [25,27,43,55,60], we use only the remaining 5 domains in the experiments. The resulting datasets contain 17 distinct slots and 30 domain slot pairs.…”

Section: Slot Value Matchingmentioning

confidence: 99%

Slot Self-Attentive Dialogue State Tracking

Manotumruksa

Zhang

et al. 2021

Preprint

View full text Add to dashboard Cite

An indispensable component in task-oriented dialogue systems is the dialogue state tracker, which keeps track of users' intentions in the course of conversation. The typical approach towards this goal is to fill in multiple pre-defined slots that are essential to complete the task. Although various dialogue state tracking methods have been proposed in recent years, most of them predict the value of each slot separately and fail to consider the correlations among slots. In this paper, we propose a slot self-attention mechanism that can learn the slot correlations automatically. Specifically, a slottoken attention is first utilized to obtain slot-specific features from the dialogue context. Then a stacked slot self-attention is applied on these features to learn the correlations among slots. We conduct comprehensive experiments on two multi-domain task-oriented dialogue datasets, including MultiWOZ 2.0 and MultiWOZ 2.1. The experimental results demonstrate that our approach achieves stateof-the-art performance on both datasets, verifying the necessity and effectiveness of taking slot correlations into consideration. CCS CONCEPTS• Computing methodologies → Natural language processing; Discourse, dialogue and pragmatics; Machine learning.

show abstract

“…Traditional DST methods can be divided into two major types: open-vocabulary (Le, Socher, and Hoi 2020;Goel, Paul, and Hakkani-Tür 2019;Wu et al 2019) and predefined-ontology (Lee, Lee, and Kim 2019;Shan et al 2020). The former one generates slot value at each turn by a generative model such as the decoder stack in RNN and Transformer, and the latter predefines the dialogue ontology and simplifies the DST models into a classification problem.…”

Section: Related Workmentioning

confidence: 99%

“…NADST: Generate dialogue state at each turn by a non-autoregressive decoder model (Le, Socher, and Hoi 2020). TRADE: Using an Encoding Decoding model to generate slot-value label (Wu et al 2019).…”

Section: Experiments Baseline Modelsmentioning

confidence: 99%

Efficient Dialogue State Tracking by Masked Hierarchical Transformer

Mao,

Liu,

Zhou

et al. 2021

Preprint

View full text Add to dashboard Cite

This paper describes our approach to DSTC 9 Track 2: Crosslingual Multi-domain Dialog State Tracking, the task goal is to build a cross-lingual dialog state tracker with a training set in rich resource language and a testing set in low resource language. We formulate a method for joint learning of slot operation classification task and state tracking task respectively. Furthermore, we design a novel mask mechanism for fusing contextual information about dialogue, the results show the proposed model achieves excellent performance on DSTC Challenge II with a joint accuracy of 62.37% and 23.96% in MultiWOZ(en → zh) dataset and CrossWOZ(zh → en) dataset, respectively.

show abstract

Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems

Cited by 31 publications

References 31 publications

GlobalWoZ: Globalizing MultiWoZ to Develop Multilingual Task-Oriented Dialogue Systems

GlobalWoZ: Globalizing MultiWoZ to Develop Multilingual Task-Oriented Dialogue Systems

Slot Self-Attentive Dialogue State Tracking

Efficient Dialogue State Tracking by Masked Hierarchical Transformer

Contact Info

Product

Resources

About