paper-with-me

홈 › Papers

Zero-shot Slot Filling in the Age of LLMs for Dialogue Systems

2024-11-28 · Mansi Rana, Kadri Hacioglu, Sindhuja Gopalan, Maragathamani Boothalingam

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.

📄 PDF Abstract BibTeX arXiv:2411.18980

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge DistillationNatural Language Understandingslot-fillingSlot FillingZero-shot Slot Filling

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…
Focus 설명 없음

Similar Papers 제목 키워드 기반

AISFG: Abundant Information Slot Filling Generator

2022-07-01 · NAACL 2022 7 · Yang Yan, Junda Ye, Zhongbao Zhang, LiWen Wang

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 Systems

HierarchicalContrast: A Coarse-to-Fine Contrastive Learning Framework for Cross-Domain Zero-Shot Slot Filling

2023-10-13 · Junwen Zhang, Yin Zhang

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+1

A Preliminary Evaluation of ChatGPT for Zero-shot Dialogue Understanding

2023-04-09 · Wenbo Pan, Qiguang Chen, Xiao Xu, Wanxiang Che 외

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+1

Semantic Parsing by Large Language Models for Intricate Updating Strategies of Zero-Shot Dialogue State Tracking

2023-10-16 · Yuxiang Wu, Guanting Dong, Weiran Xu

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+1

Knowledge-Aware Audio-Grounded Generative Slot Filling for Limited Annotated Data

2023-07-04 · Guangzhi Sun, Chao Zhang, Ivan Vulić, Paweł Budzianowski 외

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