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

Abstract

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.

v2 - fixed a citation error, unchanged from v1 otherwise

References in corpus (1)

• Multi-Label Zero-Shot Learning via Concept Embedding

Cited by in corpus (12)

• Benchmarking Zero-shot Text Classification: Datasets, Evaluation and Entailment Approach
• Integrating Semantic Knowledge to Tackle Zero-shot Text Classification
• Zero-shot learning approach to adaptive Cybersecurity using Explainable AI
• Text Classification Using Label Names Only: A Language Model Self-Training Approach
• Generalized Zero-shot ICD Coding
• Logic-guided Semantic Representation Learning for Zero-Shot Relation Classification
• Transfer Learning for Multi-lingual Tasks -- a Survey
• Adapting Language Models for Zero-shot Learning by Meta-tuning on Dataset and Prompt Collections
• Learning from Miscellaneous Other-Class Words for Few-shot Named Entity Recognition
• Zero-Shot Feature Selection via Transferring Supervised Knowledge
• MyMigrationBot: A Cloud-based Facebook Social Chatbot for Migrant Populations
• An Evaluation of Transfer Learning for Classifying Sales Engagement Emails at Large Scale