Train Once, Test Anywhere: Zero-Shot Learning for Text Classification

12/16/2017
by   Pushpankar Kumar Pushp, et al.
0

Zero-shot Learners are models capable of predicting unseen classes. In this work, we propose a Zero-shot Learning approach for text categorization. Our method involves training model on a large corpus of sentences to learn the relationship between a sentence and embedding of sentence's tags. Learning such relationship makes the model generalize to unseen sentences, tags, and even new datasets provided they can be put into same embedding space. The model learns to predict whether a given sentence is related to a tag or not; unlike other classifiers that learn to classify the sentence as one of the possible classes. We propose three different neural networks for the task and report their accuracy on the test set of the dataset used for training them as well as two other standard datasets for which no retraining was done. We show that our models generalize well across new unseen classes in both cases. Although the models do not achieve the accuracy level of the state of the art supervised models, yet it evidently is a step forward towards general intelligence in natural language processing.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/11/2019

From Fully Supervised to Zero Shot Settings for Twitter Hashtag Recommendation

We propose a comprehensive end-to-end pipeline for Twitter hashtags reco...
research
12/03/2015

Prototypical Priors: From Improving Classification to Zero-Shot Learning

Recent works on zero-shot learning make use of side information such as ...
research
04/06/2020

Zero-Shot Learning of Text Adventure Games with Sentence-Level Semantics

Reinforcement learning algorithms such as Q-learning have shown great pr...
research
01/19/2018

Investigating the Working of Text Classifiers

Text classification is one of the most widely studied task in natural la...
research
08/04/2023

Learning to Paraphrase Sentences to Different Complexity Levels

While sentence simplification is an active research topic in NLP, its ad...
research
08/06/2020

Few-Shot Drum Transcription in Polyphonic Music

Data-driven approaches to automatic drum transcription (ADT) are often l...
research
04/06/2023

TagGPT: Large Language Models are Zero-shot Multimodal Taggers

Tags are pivotal in facilitating the effective distribution of multimedi...

Please sign up or login with your details

Forgot password? Click here to reset