mlsanityData to 14 Oct 2026

Pseudo Siamese Network for Few-shot Intent Generation

arXiv 2105.00896 ↗First posted 3 May 2021cs.CLcited by 11

Not on the map. Why?

Abstract (arXiv)

Few-shot intent detection is a challenging task due to the scare annotation problem. In this paper, we propose a Pseudo Siamese Network (PSN) to generate labeled data for few-shot intents and alleviate this problem. PSN consists of two identical subnetworks with the same structure but different weights: an action network and an object network. Each subnetwork is a transformer-based variational autoencoder that tries to model the latent distribution of different components in the sentence. The action network is learned to understand action tokens and the object network focuses on object-related expressions. It provides an interpretable framework for generating an utterance with an action and an object existing in a given intent. Experiments on two real-world datasets show that PSN achieves state-of-the-art performance for the generalized few shot intent detection task.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 24 of its 28 references that are in the map. First posted on arXiv 3 May 2021.

Builds on

24 of 28 references.

References · 24

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2016Layer Normalizationcited by 5,669
  4. 2013Auto-Encoding Variational Bayescited by 4,053
  5. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  6. 2016Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translationcited by 1,475
  7. 2019EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Taskscited by 807
  8. 2019Unified Language Model Pre-training for Natural Language Understanding and Generationcited by 670
  9. 2015Generating Sentences from a Continuous Spacecited by 612
  10. 2014Semi-Supervised Learning with Deep Generative Modelscited by 496
  11. 2018Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfacescited by 377
  12. 2017Toward Controlled Generation of Textcited by 272
12 more
  1. 2017Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoderscited by 222
  2. 2019Benchmarking Natural Language Understanding Services for building Conversational Agentscited by 166
  3. 2018Zero-shot User Intent Detection via Capsule Neural Networkscited by 54
  4. 2020Discriminative Nearest Neighbor Few-Shot Intent Detection by Transferring Natural Language Inferencecited by 47
  5. 2021Augmenting Sequential Recommendation with Pseudo-Prior Items via Reversely Pre-training Transformercited by 45
  6. 2018Open-world Learning and Application to Product Classificationcited by 39
  7. 2021Incremental Few-shot Text Classification with Multi-round New Classes: Formulation, Dataset and Systemcited by 30
  8. 2020CG-BERT: Conditional Text Generation with BERT for Generalized Few-shot Intent Detectioncited by 23
  9. 2018Data Augmentation for Spoken Language Understanding via Joint Variational Generationcited by 21
  10. 2019Controlled Text Generation for Data Augmentation in Intelligent Artificial Agentscited by 21
  11. 2020Composed Variational Natural Language Generation for Few-shot Intentscited by 19
  12. 2020Dynamic Semantic Matching and Aggregation Network for Few-shot Intent Detectioncited by 17

Built on by

Cited by year

Citing papers per year: 2021: 4; 2022: 4; 2023: 1; 2024: 2.

11 papers.

  1. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 163
  2. 2021Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuningcited by 46
  3. 2021Modeling Sequences as Distributions with Uncertainty for Sequential Recommendationcited by 22
  4. 2024Modality-Aware Integration with Large Language Models for Knowledge-based Visual Question Answeringcited by 16
  5. 2022A Simple Meta-learning Paradigm for Zero-shot Intent Classification with Mixture Attention Mechanismcited by 6
  6. 2023Revisit Few-shot Intent Classification with PLMs: Direct Fine-tuning vs. Continual Pre-trainingcited by 5
  7. 2022Improving Variational Autoencoders with Density Gap-based Regularizationcited by 3
  8. 2021A Single Example Can Improve Zero-Shot Data Generationcited by 2
  9. 2022The Devil is in the Details: On Models and Training Regimes for Few-Shot Intent Classificationcited by 2
  10. 2021Exploring the Limits of Natural Language Inference Based Setup for Few-Shot Intent Detectioncited by 0
  11. 2024MaFreeI2P: A Matching-Free Image-to-Point Cloud Registration Paradigm with Active Camera Pose Retrievalcited by 0