# Seed Word Selection for Weakly-Supervised Text Classification with Unsupervised Error Estimation

arXiv: https://arxiv.org/abs/2104.09765 · HTML: https://mlsanity.com/paper/2104.09765/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 21 references that are in the map.
- First posted on arXiv 20 Apr 2021.

## Builds on (most cited first, 7 of 7)

- [Convolutional Neural Networks for Sentence Classification](https://mlsanity.com/paper/1408.5882/) (2014)
- [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)
- [Weakly-Supervised Hierarchical Text Classification](https://mlsanity.com/paper/1812.11270/) (2018)
- [Text Classification Using Label Names Only: A Language Model Self-Training Approach](https://mlsanity.com/paper/2010.07245/) (2020)
- [Estimating the Accuracies of Multiple Classifiers Without Labeled Data](https://mlsanity.com/paper/1407.7644/) (2014)
- [Limitations of Assessing Active Learning Performance at Runtime](https://mlsanity.com/paper/1901.10338/) (2019)

## Built on by (most cited first, 2 of 2)

- [Towards Weakly-Supervised Hate Speech Classification Across Datasets](https://mlsanity.com/paper/2305.02637/) (2023)
- [Weakly Supervised Text Classification on Free Text Comments in Patient-Reported Outcome Measures](https://mlsanity.com/paper/2308.06199/) (2023)

## Abstract (arXiv)

Weakly-supervised text classification aims to induce text classifiers from only a few user-provided seed words. The vast majority of previous work assumes high-quality seed words are given. However, the expert-annotated seed words are sometimes non-trivial to come up with. Furthermore, in the weakly-supervised learning setting, we do not have any labeled document to measure the seed words' efficacy, making the seed word selection process "a walk in the dark". In this work, we remove the need for expert-curated seed words by first mining (noisy) candidate seed words associated with the category names. We then train interim models with individual candidate seed words. Lastly, we estimate the interim models' error rate in an unsupervised manner. The seed words that yield the lowest estimated error rates are added to the final seed word set. A comprehensive evaluation of six binary classification tasks on four popular datasets demonstrates that the proposed method outperforms a baseline using only category name seed words and obtained comparable performance as a counterpart using expert-annotated seed words.