Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems
By Chien-Sheng Wu, Andrea Madotto, Ehsan Hosseini-Asl, Caiming Xiong, Richard Socher, Pascale Fung. 2019
481 citations recorded by the source corpus.
Over-dependence on domain ontology and lack of sharing knowledge across domains are two practical and yet less studied problems of dialogue state tracking. Existing approaches generally fall short when tracking unknown slot values during inference and often have difficulties in adapting to new domains. In this paper, we propose a Transferable Dialogue State Generator (TRADE) that generates dialogue states from utterances using copy mechanism, facilitating transfer when predicting (domain, slot, value) triplets not encountered during training. Our model is composed of an utterance encoder, a slot gate, and a state generator, which are shared across domains. Empirical results demonstrate that TRADE achieves state-of-the-art 48.62% joint goal accuracy for the five domains of MultiWOZ, a human-human dialogue dataset. In addition, we show the transferring ability by simulating zero-shot and few-shot dialogue state tracking for unseen domains. TRADE achieves 60.58% joint goal accuracy in one of the zero-shot domains, and is able to adapt to few-shot cases without forgetting already trained domains.
Subfields: Artificial Intelligence, Representation & Self-Supervised Learning, Dialogue & Conversational AI
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
- Jianfeng Gao
- Mohit Bansal
- Percy Liang
- Caiming Xiong
- Luke S. Zettlemoyer
- Richard Socher
- Noah A. Smith
- Yejin Choi
In Representation & Self-Supervised Learning
- Caiming Xiong
- Percy Liang
- Jianfeng Gao
- Zhiyuan Liu
- Erik Cambria
- Steven C. H. Hoi
- Dan Roth
- Xiao-Dan Zhu
In Dialogue & Conversational AI
- Andrea Madotto
- Zihan Liu
- Zhaojiang Lin
- Bing Liu
- Minlie Huang
- Hao Cheng
- Mari Ostendorf
- Chia-Hsuan Lee
Citations in the corpus
- Dynamic Dialogue Policy for Continual Reinforcement Learning (2022, background): “Other works concentrated on dialogue state tracking (Wu et al., 2019) or natural language generation (Mi et al.”
- Continual Learning in Task-Oriented Dialogue Systems (2020, methodology): “• DST is evaluated with the Joint Goal Accuracy (JGA) (Wu et al., 2019) over the gold dialogue state.”
- Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Dataset (2019, background): “Addressing these concerns, approaches utilizing a dynamic vocabulary of slot values have been proposed (Rastogi, Gupta, and Hakkani-Tur 2018; Goel, Paul, and Hakkani-Tür 2019; Wu et al. 2019).”
- CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases (2019, background): “These systems (Bordes and Weston, 2017; Zhong et al., 2018; Wu et al., 2019) often predefine slot templates grounded to domain-specific ontology, limiting the ability to generalize to unseen domains.”
- Speech-Language Pre-Training for End-to-End Spoken Language Understanding (2021, background): “, GPT), for NLP tasks like natural language understanding, natural language generation, or end-to-end task completion have been explored for dialog systems [16, 17, 18, 19].”
- A Survey on Conversational Recommender Systems (2020, background): “In a user-driven conversation, the recommendation seeker might, for example, explicitly ask for help [95] or make a recommendation request [154] to start the interaction.”
- Multi-domain Dialogue State Tracking as Dynamic Knowledge Graph Enhanced Question Answering (2019, methodology): “Wu et al. (2019) propose to use an encoder-decoder architecture with a pointer network.”
- MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems (2020, methodology): “Existing works either perform classifications for each slot over a candidate-value list (Zhang et al., 2019a) or directly generate slot values with a generative model (Lei et al., 2018; Wu et al., 2019a; Kim et al., 2019; Le et al., 2020).”
- Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue StateTracking (2021, methodology): “We evaluate our proposed model with 1%, 5%, and 10% in-domain data, against TRADE (Wu et al., 2019) and DSTQA (Zhou and Small, 2019).”
- MultiWOZ 2. (2019, background): “…a unique resource, in terms of its multi-domain interactions as well as slot value transfers be-tween these domains, and has quickly attracted researchers for dialogue state tracking (Nouri and Hosseini-Asl, 2018; Goel et al., 2019; Wu et al., 2019) and dialogue policy learning (Zhao et al., 2019).”
- Find or Classify? Dual Strategy for Slot-Value Predictions on Multi-Domain Dialog State Tracking (2019, methodology): “We follow recent strategies [25, 27] to predict the values for all the domainslot pairs in S at each turn.”
- TOD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialogue (2020, methodology): “We also list several well-known dialogue state trackers as reference, including DSTReader (Gao et al., 2019), HyST (Goel et al., 2019), TRADE (Wu et al., 2019), and ZS-DST (Rastogi et al., 2019).”
- Schema-Guided Multi-Domain Dialogue State Tracking with Graph Attention Neural Networks (2020, methodology): “The re-Table Error Analysis Domain-specific slot accuracy of SST-2 and TRADE 1 on MultiWOZ 2.0 test set is shown in Table 4.”
- Dialogue State Tracking with a Language Model using Schema-Driven Prompting (2021, methodology): “, 2020) or the first input of the decoder (Wu et al., 2019).”
- 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…”