Continual Few-shot Intent Detection
Intent detection is at the core of task-oriented dialogue systems. Existing intent detection systems are typically trained with a large amount of data over a predefined set of intent classes. However, newly emerged intents in multiple domains are commonplace in the real world. And it is time-consuming and impractical for dialogue systems to re-collect enough annotated data and re-train the model. These limitations call for an intent detection system that could continually recognize new intents with very few labeled examples. In this work, we study the Continual Few-shot Intent Detection (CFID) problem and construct a benchmark consisting of nine tasks with multiple domains and imbalanced classes. To address the key challenges of (a) catastrophic forgetting during continuous learning and (b) negative knowledge transfer across tasks, we propose the Prefix-guided Lightweight Encoder (PLE) with three auxiliary strategies, namely Pseudo Samples Replay (PSR), Teacher Knowledge Transfer (TKT) and Dynamic Weighting Replay (DWR). Extensive experiments demonstrate the effectiveness and efficiency of our method in preventing catastrophic forgetting and encouraging positive knowledge transfer across tasks.
Code (0)
등록된 구현이 없습니다.
Tasks
Intent DetectionTask-Oriented Dialogue SystemsTransfer LearningSimilar Papers 제목 키워드 기반
Zero-shot User Intent Detection via Capsule Neural Networks
User intent detection plays a critical role in question-answering and dialog systems. Most previous works treat intent detection as a classification problem where utterances are labeled with predefined intents. However, …
Intent DetectionQuestion AnsweringTransfer LearningZero-Shot LearningRevisit Few-shot Intent Classification with PLMs: Direct Fine-tuning vs. Continual Pre-training
We consider the task of few-shot intent detection, which involves training a deep learning model to classify utterances based on their underlying intents using only a small amount of labeled data. The current approach to…
intent-classificationIntent ClassificationIntent DetectionNatural Language UnderstandingJoint Intent Detection And Slot Filling Based on Continual Learning Model
Slot filling and intent detection have become a significant theme in the field of natural language understanding. Even though slot filling is intensively associated with intent detection, the characteristics of the infor…
Continual LearningIntent DetectionNatural Language Understandingslot-filling+1Prompt Augmented Generative Replay via Supervised Contrastive Learning for Lifelong Intent Detection
Identifying all possible user intents for a dialog system at design time is challenging even for skilled domain experts. For practical applications, novel intents may have to be inferred incrementally on the fly. This ty…
Continual LearningContrastive LearningIntent DetectionRelation ExtractionFew-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuning
In this work, we focus on a more challenging few-shot intent detection scenario where many intents are fine-grained and semantically similar. We present a simple yet effective few-shot intent detection schema via contras…
Contrastive LearningIntent Detection