DeepAI AI Chat
Log In Sign Up

Learning to Classify Intents and Slot Labels Given a Handful of Examples

by   Jason Krone, et al.
George Washington University

Intent classification (IC) and slot filling (SF) are core components in most goal-oriented dialogue systems. Current IC/SF models perform poorly when the number of training examples per class is small. We propose a new few-shot learning task, few-shot IC/SF, to study and improve the performance of IC and SF models on classes not seen at training time in ultra low resource scenarios. We establish a few-shot IC/SF benchmark by defining few-shot splits for three public IC/SF datasets, ATIS, TOP, and Snips. We show that two popular few-shot learning algorithms, model agnostic meta learning (MAML) and prototypical networks, outperform a fine-tuning baseline on this benchmark. Prototypical networks achieves significant gains in IC performance on the ATIS and TOP datasets, while both prototypical networks and MAML outperform the baseline with respect to SF on all three datasets. In addition, we demonstrate that joint training as well as the use of pre-trained language models, ELMo and BERT in our case, are complementary to these few-shot learning methods and yield further gains.


page 1

page 2

page 3

page 4


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

Recently deep learning has dominated many machine learning areas, includ...

A Baseline for Few-Shot Image Classification

Fine-tuning a deep network trained with the standard cross-entropy loss ...

Fine-Tuning BERT for Schema-Guided Zero-Shot Dialogue State Tracking

We present our work on Track 4 in the Dialogue System Technology Challen...

MetaAudio: A Few-Shot Audio Classification Benchmark

Currently available benchmarks for few-shot learning (machine learning w...

Sociocultural knowledge is needed for selection of shots in hate speech detection tasks

We introduce HATELEXICON, a lexicon of slurs and targets of hate speech ...

One of these (Few) Things is Not Like the Others

To perform well, most deep learning based image classification systems r...

Uniform Sampling over Episode Difficulty

Episodic training is a core ingredient of few-shot learning to train mod...