DeepAI AI Chat
Log In Sign Up

ProtAugment: Unsupervised diverse short-texts paraphrasing for intent detection meta-learning

05/27/2021
by   Thomas Dopierre, et al.
4

Recent research considers few-shot intent detection as a meta-learning problem: the model is learning to learn from a consecutive set of small tasks named episodes. In this work, we propose ProtAugment, a meta-learning algorithm for short texts classification (the intent detection task). ProtAugment is a novel extension of Prototypical Networks, that limits overfitting on the bias introduced by the few-shots classification objective at each episode. It relies on diverse paraphrasing: a conditional language model is first fine-tuned for paraphrasing, and diversity is later introduced at the decoding stage at each meta-learning episode. The diverse paraphrasing is unsupervised as it is applied to unlabelled data, and then fueled to the Prototypical Network training objective as a consistency loss. ProtAugment is the state-of-the-art method for intent detection meta-learning, at no extra labeling efforts and without the need to fine-tune a conditional language model on a given application domain.

READ FULL TEXT

page 1

page 2

page 3

page 4

06/29/2021

Representation based meta-learning for few-shot spoken intent recognition

Spoken intent detection has become a popular approach to interface with ...
03/02/2023

Unsupervised Meta-Learning via Few-shot Pseudo-supervised Contrastive Learning

Unsupervised meta-learning aims to learn generalizable knowledge across ...
10/12/2022

The Devil is in the Details: On Models and Training Regimes for Few-Shot Intent Classification

Few-shot Intent Classification (FSIC) is one of the key challenges in mo...
01/28/2021

ProtoDA: Efficient Transfer Learning for Few-Shot Intent Classification

Practical sequence classification tasks in natural language processing o...
11/30/2020

Meta learning to classify intent and slot labels with noisy few shot examples

Recently deep learning has dominated many machine learning areas, includ...
09/17/2021

Semi-Supervised Few-Shot Intent Classification and Slot Filling

Intent classification (IC) and slot filling (SF) are two fundamental tas...
10/15/2021

Meta-learning via Language Model In-context Tuning

The goal of meta-learning is to learn to adapt to a new task with only a...