Lune

EMNLP Findings2020

Towards Low-Resource Semi-Supervised Dialogue Generation with Meta-Learning

Yi Huang, Junlan Feng, Shuo Ma, Xiaoyu Du, Xiaoting Wu

Abstract

In this paper, we propose a meta-learning based semi-supervised explicit dialogue state tracker (SEDST) for neural dialogue generation, denoted as MEDST. Our main motivation is to further bridge the chasm between the need for high accuracy dialogue state tracker and the common reality that only scarce annotated data is available for most real-life dialogue tasks. Specifically, MEDST has two core steps: meta-training with adequate unlabelled data in an automatic way and meta-testing with a few annotated data by supervised learning. In particular, we enhance SEDST via entropy regularization, and investigate semi-supervised learning frameworks based on model-agnostic meta-learning (MAML) that are able to reduce the amount of required intermediate state labelling. We find that by leveraging un-annotated data in meta-way instead, the amount of dialogue state annotations can be reduced below 10% while maintaining equivalent system performance. Experimental results show MEDST outperforms SEDST substantially by 18.7% joint goal accuracy and 14.3% entity match rate on the KVRET corpus with 2% labelled data in semi-supervision.

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.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

Builds onCited byLeft to right by year; the more cited, the higher.

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. Meta-Reinforced Multi-Domain State Generator for Dialogue SystemsYi Huang, Junlan Feng, Min Hu, Xiaoting Wu et al.ACL 2020 · 30 citations
  3. Dialog State Tracking with Reinforced Data AugmentationYichun Yin, Lifeng Shang, Xin Jiang, Xiao Chen et al.AAAI 2020 · 25 citations

Related papers

  1. MetaASSIST: Robust Dialogue State Tracking with Meta LearningFanghua Ye, Xi Wang, Jie Huang, Shenghui Li et al.EMNLP 2022 · 10 citations
  2. Improving Limited Labeled Dialogue State Tracking with Self-SupervisionChien-Sheng Wu, Steven C. H. Hoi, Caiming XiongEMNLP Findings 2020 · 12 citations
  3. A Probabilistic End-To-End Task-Oriented Dialog Model with Latent Belief States towards Semi-Supervised LearningYichi Zhang, Zhijian Ou, Min Hu, Junlan FengEMNLP 2020 · 52 citations
  4. Exploring Auxiliary Reasoning Tasks for Task-oriented Dialog Systems with Meta Cooperative LearningBowen Qin, Min Yang, Lidong Bing, Qingshan Jiang et al.AAAI 2021 · 9 citations
  5. Dialogue Summaries as Dialogue States (DS2), Template-Guided Summarization for Few-shot Dialogue State TrackingJamin Shin, Hangyeol Yu, Hyeongdon Moon, Andrea Madotto et al.ACL Findings 2022 · 26 citations
Dusk over the sea between two cliffs drawn in fine vertical lines