N-Shot Learning for Augmenting Task-Oriented Dialogue State Tracking
원문 초록
Augmentation of task-oriented dialogues has followed standard methods used for plain-text such as back-translation, word-level manipulation, and paraphrasing despite its richly annotated structure. In this work, we introduce an augmentation framework that utilizes belief state annotations to match turns from various dialogues and form new synthetic dialogues in a bottom-up manner. Unlike other augmentation strategies, it operates with as few as five examples. Our augmentation strategy yields significant improvements when both adapting a DST model to a new domain, and when adapting a language model to the DST task, on evaluations with TRADE and TOD-BERT models. Further analysis shows that our model performs better on seen values during training, and it is also more robust to unseen values. We conclude that exploiting belief state annotations enhances dialogue augmentation and results in improved models in n-shot training scenarios.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Iceberg: Enhancing HLS Modeling with Synthetic Data
Evolution without Large Models: Training Language Model with Task Principles
Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition
Seewo's Submission to MLC-SLM: Lessons learned from Speech Reasoning Language Models
Motion-R1: Chain-of-Thought Reasoning and Reinforcement Learning for Human Motion Generation
Alzheimer's Dementia Detection Using Perplexity from Paired Large Language Models
토론
이 논문과 연결된 포럼 글이 아직 없습니다.