Intent-driven In-context Learning for Few-shot Dialogue State Tracking

2024-12-04 · Zihao Yi, Zhe Xu, Ying Shen

Dialogue state tracking (DST) plays an essential role in task-oriented dialogue systems. However, user's input may contain implicit information, posing significant challenges for DST tasks. Additionally, DST data includes complex information, which not only contains a large amount of noise unrelated to the current turn, but also makes constructing DST datasets expensive. To address these challenges, we introduce Intent-driven In-context Learning for Few-shot DST (IDIC-DST). By extracting user's intent, we propose an Intent-driven Dialogue Information Augmentation module to augment the dialogue information, which can track dialogue states more effectively. Moreover, we mask noisy information from DST data and rewrite user's input in the Intent-driven Examples Retrieval module, where we retrieve similar examples. We then utilize a pre-trained large language model to update the dialogue state using the augmented dialogue information and examples. Experimental results demonstrate that IDIC-DST achieves state-of-the-art performance in few-shot settings on MultiWOZ 2.1 and MultiWOZ 2.4 datasets.

📄 PDF Abstract BibTeX arXiv:2412.03270

Code (0)

등록된 구현이 없습니다.

Tasks

Dialogue State TrackingIn-Context LearningLanguage ModelingLanguage ModellingLarge Language ModelTask-Oriented Dialogue Systems

Methods 이 논문이 사용한 방법론

DST Dynamic sparse training methods train neural networks in a sparse manner, starting with an initial sparse mask, and periodically updating the mask based on some criteria.

DiSTRICT: Dialogue State Tracking with Retriever Driven In-Context Tuning

2022-12-06 · Praveen Venkateswaran, Evelyn Duesterwald, Vatche Isahagian

Dialogue State Tracking (DST), a key component of task-oriented conversation systems, represents user intentions by determining the values of pre-defined slots in an ongoing dialogue. Existing approaches use hand-crafted…

Dialogue State Tracking

IntentGPT: Few-shot Intent Discovery with Large Language Models

2024-11-16 · Juan A. Rodriguez, Nicholas Botzer, David Vazquez, Christopher Pal 외

In today's digitally driven world, dialogue systems play a pivotal role in enhancing user interactions, from customer service to virtual assistants. In these dialogues, it is important to identify user's goals automatica…

In-Context Learning Intent Detection Intent Discovery

InFoBERT: Zero-Shot Approach to Natural Language Understanding Using Contextualized Word Embedding

2021-09-01 · RANLP 2021 9 · Pavel Burnyshev, Andrey Bout, Valentin Malykh, Irina Piontkovskaya

Natural language understanding is an important task in modern dialogue systems. It becomes more important with the rapid extension of the dialogue systems’ functionality. In this work, we present an approach to zero-shot…

intent-classification Intent Classification Intent Classification and Slot Filling Natural Language Understanding+3

Dynamic Label Name Refinement for Few-Shot Dialogue Intent Classification

2024-12-20 · Gyutae Park, Ingeol Baek, Byeongjeong Kim, Joongbo Shin 외

Dialogue intent classification aims to identify the underlying purpose or intent of a user's input in a conversation. Current intent classification systems encounter considerable challenges, primarily due to the vast num…

In-Context Learning intent-classification Intent Classification Language Modeling+2

Stabilized In-Context Learning with Pre-trained Language Models for Few Shot Dialogue State Tracking

2023-02-12 · Derek Chen, Kun Qian, Zhou Yu

Prompt-based methods with large pre-trained language models (PLMs) have shown impressive unaided performance across many NLP tasks. These models improve even further with the addition of a few labeled in-context exemplar…

Dialogue State Tracking In-Context Learning Meta-Learning Retrieval