Findings of the Association for Computational Linguistics: ACL 2022 · 2022 · 24 citations · 48 references
ComputingComputer ScienceComputational LinguisticsNatural Language ProcessingText AnalyticsDialogue AnalysisDialogue SystemsLanguage ModelingText SummarizationDialogue SummarizationSummarizationSummary Generation ModelsTemplate-based Summarization
Annotating task-oriented dialogues is notorious for the expensive and difficult data collection process. Few-shot dialogue state tracking (DST) is a realistic solution to this problem. In this paper, we hypothesize that dialogue summaries are essentially unstructured dialogue states; hence, we propose to reformulate dialogue state tracking as a dialogue summarization problem. To elaborate, we train a text-totext language model with synthetic templatebased dialogue summaries, generated by a set of rules. Then, the dialogue states can be recovered by inversely applying the summary generation rules. We empirically show that our method DS2 outperforms previous works on few-shot DST in MultiWoZ 2.0 and 2.1, in both cross-domain and multi-domain settings. Our method 1 also exhibits vast speedup during both training and inference as it can generate all states at once. Finally, based on our analysis, we discover that the naturalness of the summary templates plays a key role for successful training.
48
ROUGE: A Package for Automatic Evaluation of Summaries
Chin-Yew Lin · 2004 · 8.3K citations
Making Pre-trained Language Models Better Few-shot Learners
Tianyu Gao, Adam Fisch, Danqi Chen · 2021 · 1.2K citations · Full text