Deep Unknown Intent Detection with Margin Loss (P19-1)

Copied to clipboard

Challenge: Existing methods for detecting unknown intents are difficult due to lack of examples.
Approach: They propose a method for detecting unknown intents using bidirectional long-term memory networks with the margin loss as the feature extractor.
Outcome: The proposed method can yield consistent improvements on two benchmark datasets.

Similar Papers

Out-of-Scope Intent Detection with Self-Supervision and Discriminative Training (2021.acl-long)

Copied to clipboard

Challenge: Existing methods for out-of-scope intent detection rely on strong assumptions on data distribution and confidence threshold selection.
Approach: They propose a method to train an out-of-scope intent classifier in a fully end-to-end manner by simulating the test scenario in training.
Outcome: The proposed method improves on four benchmark dialogue datasets and improves over state-of-the-art methods.
Intent Detection and Discovery from User Logs via Deep Semi-Supervised Contrastive Clustering (2022.naacl-main)

Copied to clipboard

Challenge: Existing approaches to intent detection rely on epoch wise clustering and classification based on labeled and unlabeled data.
Approach: They propose an end-to-end deep contrastive clustering algorithm that jointly updates model parameters and cluster centers via supervised and self-supervised learning.
Outcome: The proposed approach outperforms baselines on five public datasets and human-in-the-loop variant for practical deployment.
Class Lifelong Learning for Intent Detection via Structure Consolidation Networks (2023.findings-acl)

Copied to clipboard

Challenge: Existing intent detection models can only handle predefined intent classes in the offline environment.
Approach: They propose a method that continually learns new intent classes from new data . structure-based retrospection and contrastive knowledge distillation are used to solve these problems .
Outcome: The proposed method outperforms existing models on three benchmarks.
Adversarial Self-Supervised Learning for Out-of-Domain Detection (2021.naacl-main)

Copied to clipboard

Challenge: Existing methods for detecting out-of-domain (OOD) intents are unsupervised and require extensive labeled data.
Approach: They propose a self-supervised contrastive learning framework to model discriminative semantic features from unlabeled data.
Outcome: The proposed framework outperforms baseline methods on two public benchmark datasets with a statistically significant margin.
Modeling Discriminative Representations for Out-of-Domain Detection with Supervised Contrastive Learning (2021.acl-short)

Copied to clipboard

Challenge: Existing methods of OOD detection only focus on whether a sample is correctly classified . lack of real OOD examples leads to poor prior knowledge about these unknown intents .
Approach: They propose a supervised contrastive learning objective to minimize intra-class variance . they employ an adversarial augmentation mechanism to obtain pseudo diverse views .
Outcome: The proposed method minimizes intra-class variance by pulling together in-domain intents belonging to the same class and maximizes inter-class variation by pushing apart samples from different classes.
Intent Detection with WikiHow (2020.aacl-main)

Copied to clipboard

Challenge: Existing approaches to intent detection have limited data annotated for new domains or languages.
Approach: They propose to train a set of pretraining intent detection models on wikiHow which can predict a broad range of intended goals from many actions.
Outcome: The proposed models achieve state-of-the-art results on the Snips dataset, the Schema-Guided Dialogue dataset, and all 3 languages of the Facebook multilingual dialog datasets.
New Intent Discovery with Pre-training and Contrastive Learning (2022.acl-long)

Copied to clipboard

Challenge: Existing methods for identifying intents from unlabeled utterances are label-intensive, inefficient, and inaccurate.
Approach: They propose a multi-task strategy to leverage unlabeled data and external labeled data for representation learning.
Outcome: The proposed method outperforms state-of-the-art methods on three intent recognition benchmarks.
KNN-Contrastive Learning for Out-of-Domain Intent Classification (2022.acl-long)

Copied to clipboard

Challenge: Existing methods for OOD intent classification are limited to regions with compact or simply-connected features, which assumes no OOD intentions reside.
Approach: They propose a method that uses k-nearest neighbors to learn discriminative semantic features that are more conducive to OOD detection.
Outcome: The proposed method improves OOD detection performance while requiring no restrictions on feature distribution.
Unknown Intent Detection Using Gaussian Mixture Model with an Application to Zero-shot Intent Classification (2020.acl-main)

Copied to clipboard

Challenge: Existing methods for unknown intent detection are limited by prior knowledge of class labels.
Approach: They propose to use a Gaussian mixture model to model utterance embeddings with a distribution and inject dynamic class semantic information into Gausssian means.
Outcome: The proposed model performs well on three real task-oriented dialogue datasets in two languages.
Beyond the Known: Investigating LLMs Performance on Out-of-Domain Intent Detection (2024.lrec-main)

Copied to clipboard

Challenge: Out-of-domain (OOD) intent detection is crucial for task-oriented dialogue systems.
Approach: They conduct a comprehensive evaluation of large language models (LLMs) under various experimental settings and outline their strengths and weaknesses.
Outcome: The proposed models exhibit strong zero-shot and few-shot capabilities, but is still at a disadvantage compared to models fine-tuned with full resource.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations