Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

A Dual Prompt Learning Framework for Few-Shot Dialogue State Tracking

Domain:

natural language processing

Record type:

papersoftware
Creator:
YanLeiHuaCao
Host:avatar
Dialogue state tracking (DST) module is an important component for task-oriented dialog systems to understand users' goals and needs. Collecting dialogue state labels including slots and values can be costly, especially with the wide application of dialogue systems in more and more new-rising domains. In this paper, we focus on how to utilize the language understanding and generation ability of pre-trained language models for DST. We design a dual prompt learning framework for few-shot DST. Specifically, we consider the learning of slot generation and value generation as dual tasks, and two prompts are designed based on such a dual structure to incorporate task-related knowledge of these two tasks respectively. In this way, the DST task can be formulated as a language modeling task efficiently under few-shot settings. Experimental results on two task-oriented dialogue datasets show that the proposed method not only outperforms existing state-of-the-art few-shot methods, but also can generate unseen slots. It indicates that DST-related knowledge can be probed from PLM and utilized to address low-resource DST efficiently with the help of prompt learning.

Visit

arxiv.org

Tags

Computation and Language

Similar

Few-shot Prompt Learning vs. Fine-tuning for Cross-lingual NER in Low-Resource LanguagesA Few‐Shot Learning Approach for a Multilingual Agro‐Information Question Answering SystemFew-shot Learning with Multilingual Language ModelsFew-Shot Learning Translation from New LanguagesSemi-supervised and transfer learning for few-shot audio classificationFew-Shot Learning for Crop Mapping from Satellite Image Time Series

Few-shot Prompt Learning vs. Fine-tuning for Cross-lingual NER in Low-Resource Languages

Cross-lingual Named Entity Recognition (NER) leverages knowledge transfer between languages to ident

A Few‐Shot Learning Approach for a Multilingual Agro‐Information Question Answering System

ABSTRACT Across numerous households in Sub‐Saharan Africa, agriculture plays a crucial role. One so

Few-shot Learning with Multilingual Language Models

Large-scale generative language models such as GPT-3 are competitive few-shot learners. While these

Few-Shot Learning Translation from New Languages

Recent work shows strong transfer learning capability to unseen languages in sequence-to-sequence ne

Semi-supervised and transfer learning for few-shot audio classification

Deep Learning hat zu erheblichen Fortschritten in der Audioanalyse geführt, doch die Abhängigkeit vo

Few-Shot Learning for Crop Mapping from Satellite Image Time Series

Recently, deep learning methods have achieved promising crop mapping results. Yet, their classificat