# WOT-Class: Weakly Supervised Open-world Text Classification

arXiv: https://arxiv.org/abs/2305.12401 · HTML: https://mlsanity.com/paper/2305.12401/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 28 references that are in the map.
- First posted on arXiv 21 May 2023.

## Builds on (most cited first, 20 of 20)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [Making Pre-trained Language Models Better Few-shot Learners](https://mlsanity.com/paper/2012.15723/) (2020)
- [Deep Clustering for Unsupervised Learning of Visual Features](https://mlsanity.com/paper/1807.05520/) (2018)
- [Self-labelling via simultaneous clustering and representation learning](https://mlsanity.com/paper/1911.05371/) (2019)
- [Towards Open World Recognition](https://mlsanity.com/paper/1412.5687/) (2014)
- [Generalized Category Discovery](https://mlsanity.com/paper/2201.02609/) (2022)
- [Open-World Semi-Supervised Learning](https://mlsanity.com/paper/2102.03526/) (2021)
- [Unsupervised Domain Clusters in Pretrained Language Models](https://mlsanity.com/paper/2004.02105/) (2020)
- [AutoNovel: Automatically Discovering and Learning Novel Visual Categories](https://mlsanity.com/paper/2106.15252/) (2021)
- [The Extreme Value Machine](https://mlsanity.com/paper/1506.06112/) (2015)
- [Weakly-Supervised Neural Text Classification](https://mlsanity.com/paper/1809.01478/) (2018)
- [X-Class: Text Classification with Extremely Weak Supervision](https://mlsanity.com/paper/2010.12794/) (2020)
- [Open-world Learning and Application to Product Classification](https://mlsanity.com/paper/1809.06004/) (2018)
- [Text Classification Using Label Names Only: A Language Model Self-Training Approach](https://mlsanity.com/paper/2010.07245/) (2020)
- [Discriminative Topic Mining via Category-Name Guided Text Embedding](https://mlsanity.com/paper/1908.07162/) (2019)
- [Empower Entity Set Expansion via Language Model Probing](https://mlsanity.com/paper/2004.13897/) (2020)
- [Unseen Class Discovery in Open-world Classification](https://mlsanity.com/paper/1801.05609/) (2018)
- ["Average" Approximates "First Principal Component"? An Empirical Analysis on Representations from Neural Language Models](https://mlsanity.com/paper/2104.08673/) (2021)

## Built on by (most cited first, 6 of 6)

- [Goal-Driven Explainable Clustering via Language Descriptions](https://mlsanity.com/paper/2305.13749/) (2023)
- [TELEClass: Taxonomy Enrichment and LLM-Enhanced Hierarchical Text Classification with Minimal Supervision](https://mlsanity.com/paper/2403.00165/) (2024)
- [Incubating Text Classifiers Following User Instruction with Nothing but LLM](https://mlsanity.com/paper/2404.10877/) (2024)
- [Open-world Multi-label Text Classification with Extremely Weak Supervision](https://mlsanity.com/paper/2407.05609/) (2024)
- [A Structured Literature Review on Traditional Approaches in Current Natural Language Processing](https://mlsanity.com/paper/2505.12970/) (2025)
- [Exploring the Tradeoff Between Diversity and Discrimination for Continuous Category Discovery](https://mlsanity.com/paper/2508.11173/) (2025)

## Abstract (arXiv)

State-of-the-art weakly supervised text classification methods, while significantly reduced the required human supervision, still requires the supervision to cover all the classes of interest. This is never easy to meet in practice when human explore new, large corpora without complete pictures. In this paper, we work on a novel yet important problem of weakly supervised open-world text classification, where supervision is only needed for a few examples from a few known classes and the machine should handle both known and unknown classes in test time. General open-world classification has been studied mostly using image classification; however, existing methods typically assume the availability of sufficient known-class supervision and strong unknown-class prior knowledge (e.g., the number and/or data distribution). We propose a novel framework WOT-Class that lifts those strong assumptions. Specifically, it follows an iterative process of (a) clustering text to new classes, (b) mining and ranking indicative words for each class, and (c) merging redundant classes by using the overlapped indicative words as a bridge. Extensive experiments on 7 popular text classification datasets demonstrate that WOT-Class outperforms strong baselines consistently with a large margin, attaining 23.33% greater average absolute macro-F1 over existing approaches across all datasets. Such competent accuracy illuminates the practical potential of further reducing human effort for text classification.