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

arXiv: https://arxiv.org/abs/1712.05972 · HTML: https://mlsanity.com/paper/1712.05972/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Dec 2017.

## Built on by (most cited first, 22 of 22)

- [Adapting Language Models for Zero-shot Learning by Meta-tuning on Dataset and Prompt Collections](https://mlsanity.com/paper/2104.04670/) (2021)
- [RelationPrompt: Leveraging Prompts to Generate Synthetic Data for Zero-Shot Relation Triplet Extraction](https://mlsanity.com/paper/2203.09101/) (2022)
- [Evaluating Unsupervised Text Classification: Zero-shot and Similarity-based Approaches](https://mlsanity.com/paper/2211.16285/) (2022)
- [Learning from Miscellaneous Other-Class Words for Few-shot Named Entity Recognition](https://mlsanity.com/paper/2106.15167/) (2021)
- [CEEBERT: Cross-Domain Inference in Early Exit BERT](https://mlsanity.com/paper/2405.15039/) (2024)
- [Zero-Shot Learning for Requirements Classification: An Exploratory Study](https://mlsanity.com/paper/2302.04723/) (2023)
- [Zero-Shot Multi-Label Topic Inference with Sentence Encoders](https://mlsanity.com/paper/2304.07382/) (2023)
- [Survey on Plagiarism Detection in Large Language Models: The Impact of ChatGPT and Gemini on Academic Integrity](https://mlsanity.com/paper/2407.13105/) (2024)
- [Unraveling Social Perceptions & Behaviors towards Migrants on Twitter](https://mlsanity.com/paper/2112.06642/) (2021)
- [Towards Open-Domain Topic Classification](https://mlsanity.com/paper/2306.17290/) (2023)
- [A Multi-solution Study on GDPR AI-enabled Completeness Checking of DPAs](https://mlsanity.com/paper/2311.13881/) (2023)
- [A Pseudo Label-wise Attention Network for Automatic ICD Coding](https://mlsanity.com/paper/2106.06822/) (2021)
- [TopoBERT: Plug and Play Toponym Recognition Module Harnessing Fine-tuned BERT](https://mlsanity.com/paper/2301.13631/) (2023)
- [Company classification using zero-shot learning](https://mlsanity.com/paper/2305.01028/) (2023)
- [MARRO: Multi-headed Attention for Rhetorical Role Labeling in Legal Documents](https://mlsanity.com/paper/2503.10659/) (2025)
- [Transfer Learning for Multi-lingual Tasks -- a Survey](https://mlsanity.com/paper/2110.02052/) (2021)
- [Flexible Job Classification with Zero-Shot Learning](https://mlsanity.com/paper/2209.12678/) (2022)
- [FastClass: A Time-Efficient Approach to Weakly-Supervised Text Classification](https://mlsanity.com/paper/2212.05506/) (2022)
- [How Effective are Generative Large Language Models in Performing Requirements Classification?](https://mlsanity.com/paper/2504.16768/) (2025)
- [Label Agnostic Pre-training for Zero-shot Text Classification](https://mlsanity.com/paper/2305.16521/) (2023)
- [Coping with low data availability for social media crisis message categorisation](https://mlsanity.com/paper/2305.17211/) (2023)
- [Knowledge Graph-Enhanced Zero-Shot Topic Classification: A Multi-Strategy Comparative Study](https://mlsanity.com/paper/2605.30465/) (2026)

## Abstract (arXiv)

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.