Lune

EMNLP Findings2020

Composed Variational Natural Language Generation for Few-shot Intents

Congying Xia, Caiming Xiong, Philip S. Yu, Richard Socher

Abstract

In this paper, we focus on generating training examples for few-shot intents in the realistic imbalanced scenario. To build connections between existing many-shot intents and few-shot intents, we consider an intent as a combination of a domain and an action, and propose a composed variational natural language generator (CLANG), a transformer-based conditional variational autoencoder. CLANG utilizes two latent variables to represent the utterances corresponding to two different independent parts (domain and action) in the intent, and the latent variables are composed together to generate natural examples. Additionally, to improve the generator learning, we adopt the contrastive regularization loss that contrasts the in-class with the out-of-class utterance generation given the intent. To evaluate the quality of the generated utterances, experiments are conducted on the generalized few-shot intent detection task. Empirical results show that our proposed model achieves state-of-the-art performances on two real-world intent detection datasets.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

2 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers2

  1. PDALN: Progressive Domain Adaptation over a Pre-trained Model for Low-Resource Cross-Domain Named Entity RecognitionTao Zhang, Congying Xia, Philip S. Yu, Zhiwei Liu et al.EMNLP 2021 · 22 citations
  2. A Label-Aware BERT Attention Network for Zero-Shot Multi-Intent Detection in Spoken Language UnderstandingTing-Wei Wu, Ruolin Su, Biing-Hwang JuangEMNLP 2021 · 11 citations

Builds on1

  1. Plug and Play Language Models: A Simple Approach to Controlled Text GenerationSumanth Dathathri, Andrea Madotto, Janice Lan, Jane Hung et al.ICLR 2020 · 1,166 citations

Related papers

  1. Revisit Few-shot Intent Classification with PLMs: Direct Fine-tuning vs. Continual Pre-trainingHaode Zhang, Haowen Liang, Li-Ming Zhan, Xiao-Ming Wu et al.ACL Findings 2023 · 10 citations
  2. Making Pre-trained Language Models Better Learn Few-Shot Spoken Language Understanding in More Practical ScenariosYufan Wang, Jie Mei, Bowei Zou, Rui Fan et al.ACL Findings 2023 · 4 citations
  3. Generate then Refine: Data Augmentation for Zero-shot Intent DetectionI-Fan Lin, Faegheh Hasibi, Suzan VerberneEMNLP Findings 2024 · 5 citations
  4. Effectiveness of Pre-training for Few-shot Intent ClassificationHaode Zhang, Yuwei Zhang, Li-Ming Zhan, Jiaxin Chen et al.EMNLP Findings 2021 · 40 citations
  5. A Variational Hierarchical Model for Neural Cross-Lingual SummarizationYunlong Liang, Fandong Meng, Chulun Zhou, Jinan Xu et al.ACL 2022 · 36 citations
Dusk over the sea between two cliffs drawn in fine vertical lines