Complex networks based word embeddings

2019/10/03 by Nicolas Dugué, Dugué, Nicolas, Victor Connes +1
Computer Science · #Advanced Text Analysis Techniques #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · pdf · doi:10.48550/arxiv.1910.01489

openalex publication_date 2019/10/03 · openalex created_date 2019/10/10 · openalex updated_date 2026/07/28

Abstract

Most of the time, the first step to learn word embeddings is to build a word co-occurrence matrix. As such matrices are equivalent to graphs, complex networks theory can naturally be used to deal with such data. In this paper, we consider applying community detection, a main tool of this field, to the co-occurrence matrix corresponding to a huge corpus. Community structure is used as a way to reduce the dimensionality of the initial space. Using this community structure, we propose a method to extract word embeddings that are comparable to the state-of-the-art approaches.

Related

• Node Embedding via Word Embedding for Network Community Discovery
• LLMs Between the Nodes: Community Discovery Beyond Vectors
• Community Structure aware Embedding of Nodes in a Network
• Community Detection Guarantees Using Embeddings Learned by Node2Vec
• Overlapping Community Detection in Temporal Text Networks