Pseudo Siamese Network for Few-shot Intent Generation
arXiv:2105.00896
Abstract
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.
arXiv comment5 pages, accepted to SIGIR2021
References in corpus (13)
- Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
- Prototypical Networks for Few-shot Learning
- Semi-Supervised Learning with Deep Generative Models
- Unified Language Model Pre-training for Natural Language Understanding and Generation
- Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfaces
- EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks
- Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders
- Toward Controlled Generation of Text
- Benchmarking Natural Language Understanding Services for building Conversational Agents
- CG-BERT: Conditional Text Generation with BERT for Generalized Few-shot Intent Detection
- Discriminative Nearest Neighbor Few-Shot Intent Detection by Transferring Natural Language Inference
- Composed Variational Natural Language Generation for Few-shot Intents
- Incremental Few-shot Text Classification with Multi-round New Classes: Formulation, Dataset and System