Exploring Description-Augmented Dataless Intent Classification
Not on the map. Why?
Abstract (arXiv)
In this work, we introduce several schemes to leverage description-augmented embedding similarity for dataless intent classification using current state-of-the-art (SOTA) text embedding models. We report results of our methods on four commonly used intent classification datasets and compare against previous works of a similar nature. Our work shows promising results for dataless classification scaling to a large number of unseen intents. We show competitive results and significant improvements (+6.12% Avg.) over strong zero-shot baselines, all without training on labelled or task-specific data. Furthermore, we provide qualitative error analysis of the shortfalls of this methodology to help guide future research in this area.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 33 of its 58 references that are in the map. First posted on arXiv 25 Jul 2024.
Builds on
33 of 58 references.
References · 33
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
- 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
- 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,216
- 2023Towards General Text Embeddings with Multi-stage Contrastive Learningcited by 705
- 2023Textbooks Are All You Need II: phi-1.5 technical reportcited by 559
- 2023Zephyr: Direct Distillation of LM Alignmentcited by 498
- 2021Large Dual Encoders Are Generalizable Retrieverscited by 454
- 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
- 2019An Evaluation Dataset for Intent Classification and Out-of-Scope Predictioncited by 378
- 2018Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfacescited by 376
- 2022Text and Code Embeddings by Contrastive Pre-Trainingcited by 358
21 more
- 2022One Embedder, Any Task: Instruction-Finetuned Text Embeddingscited by 329
- 2019Benchmarking Zero-shot Text Classification: Datasets, Evaluation and Entailment Approachcited by 299
- 2016A Network-based End-to-End Trainable Task-oriented Dialogue Systemcited by 252
- 2019BERT for Joint Intent Classification and Slot Fillingcited by 195
- 2022MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languagescited by 142
- 2021Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue Systemcited by 139
- 2022RetroMAE: Pre-Training Retrieval-oriented Language Models Via Masked Auto-Encodercited by 118
- 2024Stable LM 2 1.6B Technical Reportcited by 86
- 2018Zero-shot User Intent Detection via Capsule Neural Networkscited by 54
- 2020Recent Neural Methods on Slot Filling and Intent Classification for Task-Oriented Dialogue Systems: A Surveycited by 51
- 2023IDAS: Intent Discovery with Abstractive Summarizationcited by 22
- 2021Uncovering Main Causalities for Long-tailed Information Extractioncited by 21
- 2021ProtAugment: Unsupervised diverse short-texts paraphrasing for intent detection meta-learningcited by 18
- 2022Label Semantic Aware Pre-training for Few-shot Text Classificationcited by 18
- 2022Few-Shot Learning with Siamese Networks and Label Tuningcited by 15
- 2017Multi-label Dataless Text Classification with Topic Modelingcited by 14
- 2020Unsupervised Label Refinement Improves Dataless Text Classificationcited by 9
- 2022A Simple Meta-learning Paradigm for Zero-shot Intent Classification with Mixture Attention Mechanismcited by 6
- 2016Joint Embedding of Hierarchical Categories and Entities for Concept Categorization and Dataless Classificationcited by 5
- 2022Template-based Approach to Zero-shot Intent Recognitioncited by 5
- 2023The Benefits of Label-Description Training for Zero-Shot Text Classificationcited by 4
Built on by
Not cited yet.