MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems

Lin, Zhaojiang; Madotto, Andrea; Winata, Genta Indra; Fung, Pascale

doi:10.18653/v1/2020.emnlp-main.273

Cited by 89 publications

(107 citation statements)

References 32 publications

(38 reference statements)

Supporting

Mentioning

105

Contrasting

Order By: Relevance

“…In this paper, we model task-oriented dialogue systems as a seq2seq generation task (Lei et al, 2018;Lin et al, 2020b;Byrne et al, 2020;Lin et al, 2021) that generates both API-calls and system responses. As shown in Figure 2, the model takes as input a dialogue history, which is the concate-nation of user intents and current dialogue states, and then uses its API-call returns, which can be empty or system speech-acts, to generate its system response.…”

Section: Task-oriented Dialogue Modellingmentioning

confidence: 99%

Continual Learning in Task-Oriented Dialogue Systems

Madotto¹,

Lin²,

Zhou³

et al. 2021

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

Self Cite

View full text Add to dashboard Cite

Continual learning in task-oriented dialogue systems allows the system to add new domains and functionalities over time after deployment, without incurring the high cost of retraining the whole system each time. In this paper, we propose a first-ever continual learning benchmark for task-oriented dialogue systems with 37 domains to be learned continuously in both modularized and end-to-end learning settings. In addition, we implement and compare multiple existing continual learning baselines, and we propose a simple yet effective architectural method based on residual adapters. We also suggest that the upper bound performance of continual learning should be equivalent to multitask learning when data from all domain is available at once. Our experiments demonstrate that the proposed architectural method and a simple replay-based strategy perform better, by a large margin, compared to other continuous learning techniques, and only slightly worse than the multitask learning upper bound while being 20X faster in learning new domains. We also report several trade-offs in terms of parameter usage, memory size and training time, which are important in the design of a task-oriented dialogue system. The proposed benchmark is released to promote more research in this direction 1 .

show abstract

Section: Task-oriented Dialogue Modellingmentioning

confidence: 99%

Continual Learning in Task-Oriented Dialogue Systems

Madotto¹,

Lin²,

Zhou³

et al. 2021

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

Self Cite

View full text Add to dashboard Cite

show abstract

“…RL methods have been used effectively to optimize end-to-end DSs in (Dhingra et al, 2017;Zhao et al, 2019), although using rule-based USs or a fixed corpus for interaction. Recent works utilise powerful transformers such as GPT-2 (Peng et al, 2020;Hosseini-Asl et al, 2020) or T5 (Lin et al, 2020b) for dialogue modeling and reach stateof-the-art performance; however, the area of having a user simulator involved during training is unexplored. By comparison, this work uses a learned US as the environment for RL.…”

Section: Related Workmentioning

confidence: 99%

Transferable Dialogue Systems and User Simulators

Tseng¹,

Dai²,

Kreyssig³

et al. 2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

View full text Add to dashboard Cite

One of the difficulties in training dialogue systems is the lack of training data. We explore the possibility of creating dialogue data through the interaction between a dialogue system and a user simulator. Our goal is to develop a modelling framework that can incorporate new dialogue scenarios through self-play between the two agents. In this framework, we first pre-train the two agents on a collection of source domain dialogues, which equips the agents to converse with each other via natural language. With further fine-tuning on a small amount of target domain data, the agents continue to interact with the aim of improving their behaviors using reinforcement learning with structured reward functions. In experiments on the MultiWOZ dataset, two practical transfer learning problems are investigated: 1) domain adaptation and 2) single-to-multiple domain transfer. We demonstrate that the proposed framework is highly effective in bootstrapping the performance of the two agents in transfer learning. We also show that our method leads to improvements in dialogue system performance on complete datasets.

show abstract

“…Dialogue Systems are categorized into chit-chat (Vinyals and Le, 2015;Serban et al, 2016) and task-oriented (Williams and Young, 2007;Young et al, 2013); in this paper we focus on the latter. Task-oriented dialogue systems are further classified into: modularized (Levin et al, 2000;Hori et al, 2009;Lee et al, 2009), retrieval (Henderson et al, 2019; end-to-end (Bordes and Weston, 2017;Eric et al, 2017a;Eric and Manning, 2017;Madotto et al, 2018;Madotto et al, 2020a;Neelakantan et al, 2019;He et al, 2020) and hybrid (Shu et al, 2018;Lei et al, 2018;Zhang et al, 2019a;Mehri et al, 2019;Peng et al, 2020a;Ham et al, 2020;Hosseini-Asl et al, 2020;Le et al, 2020;Lin et al, 2020). To the best of our knowledge, these methods use either DST/S-ACT annotations, template responses, or all/partial KB as the input to the model, where instead we only use the dialogue history.…”

Section: Related Workmentioning

confidence: 99%

Learning Knowledge Bases with Parameters for Task-Oriented Dialogue Systems

Madotto¹,

Cahyawijaya²,

Winata³

et al. 2020

Findings of the Association for Computational Linguistics: EMNLP 2020

Self Cite

View full text Add to dashboard Cite

Task-oriented dialogue systems are either modularized with separate dialogue state tracking (DST) and management steps or end-to-end trainable. In either case, the knowledge base (KB) plays an essential role in fulfilling user requests. Modularized systems rely on DST to interact with the KB, which is expensive in terms of annotation and inference time. Endto-end systems use the KB directly as input, but they cannot scale when the KB is larger than a few hundred entries. In this paper, we propose a method to embed the KB, of any size, directly into the model parameters. The resulting model does not require any DST or template responses, nor the KB as input, and it can dynamically update its KB via finetuning. We evaluate our solution in five taskoriented dialogue datasets with small, medium, and large KB size. Our experiments show that end-to-end models can effectively embed knowledge bases in their parameters and achieve competitive performance in all evaluated datasets 1 .

show abstract

MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems

Cited by 89 publications

References 32 publications

Continual Learning in Task-Oriented Dialogue Systems

Continual Learning in Task-Oriented Dialogue Systems

Transferable Dialogue Systems and User Simulators

Learning Knowledge Bases with Parameters for Task-Oriented Dialogue Systems

Contact Info

Product

Resources

About