Lune

EMNLP Findings2020

Continual Learning for Natural Language Generation in Task-oriented Dialog Systems

Fei Mi, Liangwei Chen, Mengjie Zhao, Minlie Huang, Boi Faltings

Abstract

Natural language generation (NLG) is an essential component of task-oriented dialog systems. Despite the recent success of neural approaches for NLG, they are typically developed in an offline manner for particular domains. To better fit real-life applications where new data come in a stream, we study NLG in a "continual learning" setting to expand its knowledge to new domains or functionalities incrementally. The major challenge towards this goal is catastrophic forgetting, meaning that a continually trained model tends to forget the knowledge it has learned before. To this end, we propose a method called ARPER (Adaptively Regularized Prioritized Exemplar Replay) by replaying prioritized historical exemplars, together with an adaptive regularization technique based on Elastic Weight Consolidation. Extensive experiments to continually learn new domains and intents are conducted on MultiWoZ-2.0 to benchmark ARPER with a wide range of techniques. Empirical results demonstrate that ARPER significantly outperforms other methods by effectively mitigating the detrimental catastrophic forgetting issue.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

23 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Continual Sequence Generation with Adaptive Compositional Modules cites Continual Learning in Task-Oriented Dialogue Systems
  • CINS: Comprehensive Instruction for Few-Shot Learning in Task-Oriented Dialog Systems cites Few-shot Natural Language Generation for Task-Oriented Dialog
  • Fine-tuned Language Models are Continual Learners cites Continual Learning in Task-Oriented Dialogue Systems
  • Co-Transport for Class-Incremental Learning cites Maintaining Discrimination and Fairness in Class Incremental Learning
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers23

  1. Co-Transport for Class-Incremental LearningDa-Wei Zhou, Han-Jia Ye, De-Chuan ZhanACM MM 2021 · 76 citations
  2. Continual Learning in Task-Oriented Dialogue SystemsAndrea Madotto, Zhaojiang Lin, Zhenpeng Zhou, Seungwhan Moon et al.EMNLP 2021 · 68 citations
  3. Continual Sequence Generation with Adaptive Compositional ModulesYanzhe Zhang, Xuezhi Wang, Diyi YangACL 2022 · 53 citations
  4. CINS: Comprehensive Instruction for Few-Shot Learning in Task-Oriented Dialog SystemsFei Mi, Yasheng Wang, Yitong LiAAAI 2022 · 46 citations
  5. Fine-tuned Language Models are Continual LearnersThomas Scialom, Tuhin Chakrabarty, Smaranda MuresanEMNLP 2022 · 46 citations

Builds on3

  1. Few-shot Natural Language Generation for Task-Oriented DialogBaolin Peng, Chenguang Zhu, Chunyuan Li, Xiujun Li et al.EMNLP Findings 2020 · 164 citations
  2. Recall and Learn: Fine-tuning Deep Pretrained Language Models with Less ForgettingSanyuan Chen, Yutai Hou, Yiming Cui, Wanxiang Che et al.EMNLP 2020 · 152 citations
  3. Maintaining Discrimination and Fairness in Class Incremental LearningBowen Zhao, Xi Xiao, Guojun Gan, Bin Zhang et al.CVPR 2020

Related papers

  1. Total Recall: a Customized Continual Learning Method for Neural Semantic ParsersZhuang Li, Lizhen Qu, Gholamreza HaffariEMNLP 2021 · 11 citations
  2. Prompt Conditioned VAE: Enhancing Generative Replay for Lifelong Learning in Task-Oriented DialogueYingxiu Zhao, Yinhe Zheng, Zhiliang Tian, Chang Gao et al.EMNLP 2022 · 7 citations
  3. Continual Dialogue State Tracking via Example-Guided Question AnsweringHyundong Cho, Andrea Madotto, Zhaojiang Lin, Khyathi Raghavi Chandu et al.EMNLP 2023
  4. Progressive Prompts: Continual Learning for Language ModelsAnastasia Razdaibiedina, Yuning Mao, Rui Hou, Madian Khabsa et al.ICLR 2023 · 15 citations
  5. Overcoming Catastrophic Forgetting by Exemplar Selection in Task-oriented Dialogue SystemChen Chen, Ruizhe Li, Yuchen Hu, Yuanyuan Chen et al.ACL Findings 2024 · 4 citations
Dusk over the sea between two cliffs drawn in fine vertical lines