Word sense induction using word embeddings and community detection in complex networks
arXiv:1803.08476 · doi:10.1016/j.physa.2019.02.032
Abstract
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.
References in corpus (15)
- Efficient Estimation of Word Representations in Vector Space
- Fast unfolding of communities in large networks
- Modularity and community structure in networks
- Community detection in graphs
- Natural Language Processing (almost) from Scratch
- Using network science and text analytics to produce surveys in a scientific topic
- Text authorship identified using the dynamics of word co-occurrence networks
- A complex network approach to stylometry
- Word sense disambiguation: a complex network approach
- Probing the topological properties of complex networks modeling short written texts
- Comparing the writing style of real and artificial papers
- Word sense disambiguation via high order of learning in complex networks
- On the use of topological features and hierarchical characterization for disambiguating names in collaborative networks
- Unveiling the relationship between complex networks metrics and word senses
- Robust clustering of languages across Wikipedia growth
Cited by in corpus (9)
- Decoding ChatGPT: A Taxonomy of Existing Research, Current Challenges, and Possible Future Directions
- Semantic flow in language networks
- How much does a word weigh? Weighting word embeddings for word sense induction
- Complex systems: features, similarity and connectivity
- Graph machine learning for flight delay prediction due to holding manouver
- Language Networks: a Practical Approach
- Word Sense Induction with Hierarchical Clustering and Mutual Information Maximization
- Russian word sense induction by clustering averaged word embeddings
- Hybrid Improved Document-level Embedding (HIDE)