Document Network Projection in Pretrained Word Embedding Space - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

Document Network Projection in Pretrained Word Embedding Space

Résumé

We present Regularized Linear Embedding (RLE), a novel method that projects a collection of linked documents (e.g. citation network) into a pretrained word embedding space. In addition to the textual content, we leverage a matrix of pairwise similarities providing complementary information (e.g., the network proximity of two documents in a citation graph). We first build a simple word vector average for each document, and we use the similarities to alter this average representation. The document representations can help to solve many information retrieval tasks, such as recommendation, classification and clustering. We demonstrate that our approach outperforms or matches existing document network embedding methods on node classification and link prediction tasks. Furthermore, we show that it helps identifying relevant keywords to describe document classes.

Dates et versions

hal-02515852 , version 1 (23-03-2020)

Identifiants

Citer

Antoine Gourru, Adrien Guille, Julien Velcin, Julien Jacques. Document Network Projection in Pretrained Word Embedding Space. 42nd European Conference on IR Research, ECIR 2020, Apr 2020, Lisbonne, France. ⟨hal-02515852⟩
19 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More