Skip to Main content Skip to Navigation
Conference papers

Apprentissage de plongements lexicaux par une approche réseaux complexes

Abstract : Complex networks based word embeddings. 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.
Complete list of metadata

Cited literature [26 references]  Display  Hide  Download
Contributor : Nicolas Dugue Connect in order to contact the contributor
Submitted on : Thursday, December 12, 2019 - 6:34:24 PM
Last modification on : Wednesday, October 27, 2021 - 4:33:33 AM
Long-term archiving on: : Friday, March 13, 2020 - 11:39:47 PM


Files produced by the author(s)


  • HAL Id : hal-02408156, version 1


Victor Connes, Nicolas Dugué. Apprentissage de plongements lexicaux par une approche réseaux complexes. TALN 2019, Jul 2019, Toulouse, France. ⟨hal-02408156⟩



Record views


Files downloads