paper-with-me

홈 › Papers

Generalized Intent Discovery: Learning from Open World Dialogue System

2022-09-13 · COLING 2022 10 · Yutao Mou, Keqing He, Yanan Wu, Pei Wang, Jingang Wang, Wei Wu, Yi Huang, Junlan Feng, Weiran Xu

Traditional intent classification models are based on a pre-defined intent set and only recognize limited in-domain (IND) intent classes. But users may input out-of-domain (OOD) queries in a practical dialogue system. Such OOD queries can provide directions for future improvement. In this paper, we define a new task, Generalized Intent Discovery (GID), which aims to extend an IND intent classifier to an open-world intent set including IND and OOD intents. We hope to simultaneously classify a set of labeled IND intent classes while discovering and recognizing new unlabeled OOD types incrementally. We construct three public datasets for different application scenarios and propose two kinds of frameworks, pipeline-based and end-to-end for future work. Further, we conduct exhaustive experiments and qualitative analysis to comprehend key challenges and provide new guidance for future GID research.

📄 PDF Abstract BibTeX arXiv:2209.06030

Code (1)

myt517/gid_benchmark 공식 구현 pytorch

Tasks

intent-classificationIntent ClassificationIntent Discovery

Similar Papers 제목 키워드 기반

Continual Generalized Intent Discovery: Marching Towards Dynamic and Open-world Intent Recognition

2023-10-16 · Xiaoshuai Song, Yutao Mou, Keqing He, Yueyan Qiu 외

In a practical dialogue system, users may input out-of-domain (OOD) queries. The Generalized Intent Discovery (GID) task aims to discover OOD intents from OOD queries and extend them to the in-domain (IND) classifier. Ho…

Intent DiscoveryIntent Recognition

Large Language Models Meet Open-World Intent Discovery and Recognition: An Evaluation of ChatGPT

2023-10-16 · Xiaoshuai Song, Keqing He, Pei Wang, Guanting Dong 외

The tasks of out-of-domain (OOD) intent discovery and generalized intent discovery (GID) aim to extend a closed intent classifier to open-world intent sets, which is crucial to task-oriented dialogue (TOD) systems. Previ…

In-Context LearningIntent Discovery

Benchmark Data and Evaluation Framework for Intent Discovery Around COVID-19 Vaccine Hesitancy

2022-05-24 · Shai Gretz, Assaf Toledo, Roni Friedman, Dan Lahav 외

The COVID-19 pandemic has made a huge global impact and cost millions of lives. As COVID-19 vaccines were rolled out, they were quickly met with widespread hesitancy. To address the concerns of hesitant people, we launch…

8kIntent Discovery

Towards Open Intent Discovery for Conversational Text

2019-04-17 · Nikhita Vedula, Nedim Lipka, Pranav Maneriker, Srinivasan Parthasarathy

Detecting and identifying user intent from text, both written and spoken, plays an important role in modelling and understand dialogs. Existing research for intent discovery model it as a classification task with a prede…

Intent DiscoveryOpen Intent Discovery

Decoupling Pseudo Label Disambiguation and Representation Learning for Generalized Intent Discovery

2023-05-28 · Yutao Mou, Xiaoshuai Song, Keqing He, Chen Zeng 외

Generalized intent discovery aims to extend a closed-set in-domain intent classifier to an open-world intent set including in-domain and out-of-domain intents. The key challenges lie in pseudo label disambiguation and re…

Intent DiscoveryPseudo LabelRepresentation Learning