Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

natural-language-processing-7

Open Intent Detection

3260 papers • 126 benchmarks • 313 datasets

Open intent detection aims to identify n-class known intents, and detect one-class open intent.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in open-intent-detection-7

Trend

Dataset

Best Model

Actions

BANKING77 (25%known)

BANKING-77 (50% known)

Libraries

Use these libraries to find open-intent-detection-7 models and implementations

thuiar/textoir

2 papers 177

Datasets

Banking_CG

OOS_CG

StackOverflow_CG

Subtasks

No subtasks available.

Most implemented papers

TEXTOIR: An Integrated and Visualized Platform for Text Open Intent Recognition

Hanlei Zhang, Xiaoteng Li, Hua Xu, Panpan Zhang, K. Zhao, Kai Gao•Sat Jul 31 2021

TEXTOIR provides useful toolkits and convenient visualized interfaces for each sub-module, and designs a framework to implement a complete process to both identify known intents and discover open intents.

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

BANKING-77 (75% known)

OOS(25%known)

OOS(50%known)

OOS(75%known)

SNIPS (25% known)

SNIPS (50% known)

SNIPS (75% known)

ATIS (25% known)

ATIS (50% known)

StackOverFlow(25%known)

StackOverFlow(50%known)

StackOverFlow(75%known)

Banking_CG

OOS_CG

StackOverflow_CG

Paper Graph

Deep Open Intent Classification with Adaptive Decision Boundary

Hanlei Zhang, Hua Xu, Ting-En Lin•Thu Dec 17 2020

A post-processing method to learn the adaptive decision boundary (ADB) for open intent classification by utilizing the labeled known intent samples to pre-train the model and proposing a new loss function to balance both the empirical risk and the open space risk.

120 0

Paper Graph

Deep Unknown Intent Detection with Margin Loss

Hua Xu, Ting-En Lin•Sat Jun 01 2019

This paper uses bidirectional long short-term memory network with the margin loss as the feature extractor, and feeds the feature vectors to the density-based novelty detection algorithm, local outlier factor (LOF), to detect unknown intents.

155 0

Paper Graph

Learning Discriminative Representations and Decision Boundaries for Open Intent Detection

Hanlei Zhang, Qianrui Zhou, Shaojie Zhao, Huan Xu•Thu Mar 10 2022

This article presents an original framework called DA-ADB, which successively learns distance-aware intent representations and adaptive decision boundaries for open intent detection and designs a novel loss function to obtain appropriate decision boundaries by balancing both empirical and open space risks.

28 0

Paper Graph

ChatGPT as Data Augmentation for Compositional Generalization: A Case Study in Open Intent Detection

Xiao-Dan Zhu, Yihao Fang, Xianzhi Li, Stephen W. Thomas•Thu Aug 24 2023

By incorporating synthetic data generated by ChatGPT into the training process, it is demonstrated that the approach can effectively improve model performance and outperforms existing techniques and significantly enhances open intent detection capabilities.

14 0

Paper Graph

Metric Learning and Adaptive Boundary for Out-of-Domain Detection

Petro Marek, Jakub Konrád, Petr Lorenc, Jan Pichl, J. Sedivý, Tommaso Gargiani, Ondrej Kobza•Thu Apr 21 2022

This work has designed an OOD detection algorithm independent of OOD data that outperforms a wide range of current state-of-the-art algorithms on publicly available datasets and has significantly improved OOD performance in a scenario with a lower number of classes while preserving the accuracy for in-domain (IND) classes.

0 0

Paper Graph

Adding a benchmark result helps the community track progress.

Open Intent Detection | State-of-the-Art