SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2210.17541 · EMNLP · 2022

Zero-Shot Text Classification with Self-Training

Yotam Perlitz, Eyal Shnarch, Ariel Gera, Noam Slonim, Alon Halfon, Liat Ein-Dor

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Recent advances in large pretrained language models have increased attention to zero-shot text classification. In particular, models finetuned on natural language inference datasets have been widely adopted as zero-shot classifiers due to their promising results and offthe-shelf availability. However, the fact that such models are unfamiliar with the target task can lead to instability and performance issues. We propose a plug-and-play method to bridge this gap using a simple self-training approach, requiring only the class names along with an unlabeled dataset, and without the need for domain expertise or trial and error. We show that fine-tuning the zero-shot classifier on its most confident predictions leads to significant performance gains across a wide range of text classification tasks, presumably since self-training adapts the zero-shot model to the task at hand.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2210.17541")
get_code_for_paper("2210.17541")
have("2210.17541")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2210.17541.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2210.17541.svg)](https://syntology.ai/paper/2210.17541)

Connect an agent — have() is free.