# Word sense induction using word embeddings and community detection in complex networks

arXiv: https://arxiv.org/abs/1803.08476 · HTML: https://mlsanity.com/paper/1803.08476/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Mar 2018.

## Built on by (most cited first, 5 of 5)

- [Decoding ChatGPT: A Taxonomy of Existing Research, Current Challenges, and Possible Future Directions](https://mlsanity.com/paper/2307.14107/) (2023)
- [Cognitive network science for understanding online social cognitions: A brief review](https://mlsanity.com/paper/2102.12799/) (2021)
- [Graph machine learning for flight delay prediction due to holding manouver](https://mlsanity.com/paper/2502.04233/) (2025)
- [Word Sense Induction with Hierarchical Clustering and Mutual Information Maximization](https://mlsanity.com/paper/2210.05422/) (2022)
- [Leveraging GANs for citation intent classification and its impact on citation network analysis](https://mlsanity.com/paper/2505.21162/) (2025)

## Abstract (arXiv)

Word Sense Induction (WSI) is the ability to automatically induce word senses from corpora. The WSI task was first proposed to overcome the limitations of manually annotated corpus that are required in word sense disambiguation systems. Even though several works have been proposed to induce word senses, existing systems are still very limited in the sense that they make use of structured, domain-specific knowledge sources. In this paper, we devise a method that leverages recent findings in word embeddings research to generate context embeddings, which are embeddings containing information about the semantical context of a word. In order to induce senses, we modeled the set of ambiguous words as a complex network. In the generated network, two instances (nodes) are connected if the respective context embeddings are similar. Upon using well-established community detection methods to cluster the obtained context embeddings, we found that the proposed method yields excellent performance for the WSI task. Our method outperformed competing algorithms and baselines, in a completely unsupervised manner and without the need of any additional structured knowledge source.