mlsanityData to 7 Oct 2026

CG-BERT: Conditional Text Generation with BERT for Generalized Few-shot Intent Detection

arXiv 2004.01881 ↗First posted 4 Apr 2020cs.CL cs.LGcited by 23

Not on the map. Why?

Abstract (arXiv)

In this paper, we formulate a more realistic and difficult problem setup for the intent detection task in natural language understanding, namely Generalized Few-Shot Intent Detection (GFSID). GFSID aims to discriminate a joint label space consisting of both existing intents which have enough labeled data and novel intents which only have a few examples for each class. To approach this problem, we propose a novel model, Conditional Text Generation with BERT (CG-BERT). CG-BERT effectively leverages a large pre-trained language model to generate text conditioned on the intent label. By modeling the utterance distribution with variational inference, CG-BERT can generate diverse utterances for the novel intents even with only a few utterances available. Experimental results show that CG-BERT achieves state-of-the-art performance on the GFSID task with 1-shot and 5-shot settings on two real-world datasets.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 9; 2022: 3; 2023: 8; 2024: 3.

23 papers.

Sort:

By area:

  1. 2021GPT3Mix: Leveraging Large-scale Language Models for Text Augmentationcited by 185
  2. 2023Increasing Diversity While Maintaining Accuracy: Text Data Generation with Large Language Models and Human Interventionscited by 121
  3. 2021Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuningcited by 46
  4. 2021Augmenting Sequential Recommendation with Pseudo-Prior Items via Reversely Pre-training Transformercited by 45
  5. 2021FlipDA: Effective and Robust Data Augmentation for Few-Shot Learningcited by 32
  6. 2021Incremental Few-shot Text Classification with Multi-round New Classes: Formulation, Dataset and Systemcited by 30
  7. 2023Mixture of Soft Prompts for Controllable Data Generationcited by 23
  8. 2023CoF-CoT: Enhancing Large Language Models with Coarse-to-Fine Chain-of-Thought Prompting for Multi-domain NLU Taskscited by 18
  9. 2021Pseudo Siamese Network for Few-shot Intent Generationcited by 11
  10. 2023Enhancing Cross-lingual Transfer via Phonemic Transcription Integrationcited by 11
  11. 2024Generate then Refine: Data Augmentation for Zero-shot Intent Detectioncited by 6
  12. 2024Prompting with Phonemes: Enhancing LLMs' Multilinguality for Non-Latin Script Languagescited by 6
11 more
  1. 2022Attend, Memorize and Generate: Towards Faithful Table-to-Text Generation in Few Shotscited by 5
  2. 2023Revisit Few-shot Intent Classification with PLMs: Direct Fine-tuning vs. Continual Pre-trainingcited by 5
  3. 2021Controlled Cue Generation for Play Scriptscited by 4
  4. 2023Slot Induction via Pre-trained Language Model Probing and Multi-level Contrastive Learningcited by 4
  5. 2024CORI: CJKV Benchmark with Romanization Integration -- A step towards Cross-lingual Transfer Beyond Textual Scriptscited by 4
  6. 2022Synthetic Text Detection: Systemic Literature Reviewcited by 2
  7. 2023Steering Language Generation: Harnessing Contrastive Expert Guidance and Negative Prompting for Coherent and Diverse Synthetic Data Generationcited by 2
  8. 2022Beyond Plain Toxic: Detection of Inappropriate Statements on Flammable Topics for the Russian Languagecited by 1
  9. 2021Joint Text and Label Generation for Spoken Language Understandingcited by 0
  10. 2021Exploring the Limits of Natural Language Inference Based Setup for Few-Shot Intent Detectioncited by 0
  11. 2023Data Augmentation for Improving Tail-traffic Robustness in Skill-routing for Dialogue Systemscited by 0