Zero-shot Slot Filling in the Age of LLMs for Dialogue Systems
Zero-shot slot filling is a well-established subtask of Natural Language Understanding (NLU). However, most existing methods primarily focus on single-turn text data, overlooking the unique complexities of conversational dialogue. Conversational data is highly dynamic, often involving abrupt topic shifts, interruptions, and implicit references that make it difficult to directly apply zero-shot slot filling techniques, even with the remarkable capabilities of large language models (LLMs). This paper addresses these challenges by proposing strategies for automatic data annotation with slot induction and black-box knowledge distillation (KD) from a teacher LLM to a smaller model, outperforming vanilla LLMs on internal datasets by 26% absolute increase in F1 score. Additionally, we introduce an efficient system architecture for call center product settings that surpasses off-the-shelf extractive models by 34% relative F1 score, enabling near real-time inference on dialogue streams with higher accuracy, while preserving low latency.
Code (0)
등록된 구현이 없습니다.
Tasks
Knowledge DistillationNatural Language Understandingslot-fillingSlot FillingZero-shot Slot FillingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
AISFG: Abundant Information Slot Filling Generator
As an essential component of task-oriented dialogue systems, slot filling requires enormous labeled training data in a certain domain. However, in most cases, there is little or no target domain training data is availabl…
Few-Shot Learningslot-fillingSlot FillingTask-Oriented Dialogue SystemsHierarchicalContrast: A Coarse-to-Fine Contrastive Learning Framework for Cross-Domain Zero-Shot Slot Filling
In task-oriented dialogue scenarios, cross-domain zero-shot slot filling plays a vital role in leveraging source domain knowledge to learn a model with high generalization ability in unknown target domain where annotated…
Contrastive Learningslot-fillingSlot FillingTransfer Learning+1A Preliminary Evaluation of ChatGPT for Zero-shot Dialogue Understanding
Zero-shot dialogue understanding aims to enable dialogue to track the user's needs without any training data, which has gained increasing attention. In this work, we investigate the understanding ability of ChatGPT for z…
Dialogue State TrackingDialogue Understandingslot-fillingSlot Filling+1Semantic Parsing by Large Language Models for Intricate Updating Strategies of Zero-Shot Dialogue State Tracking
Zero-shot Dialogue State Tracking (DST) addresses the challenge of acquiring and annotating task-oriented dialogues, which can be time-consuming and costly. However, DST extends beyond simple slot-filling and requires ef…
Dialogue State TrackingIn-Context LearningSemantic Parsingslot-filling+1Knowledge-Aware Audio-Grounded Generative Slot Filling for Limited Annotated Data
Manually annotating fine-grained slot-value labels for task-oriented dialogue (ToD) systems is an expensive and time-consuming endeavour. This motivates research into slot-filling methods that operate with limited amount…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)slot-fillingSlot Filling+6