Gaussian Embedding of Linked Documents from a Pretrained Semantic Space - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Gaussian Embedding of Linked Documents from a Pretrained Semantic Space

Résumé

Gaussian Embedding of Linked Documents (GELD) is a new method that embeds linked documents (e.g., citation networks) onto a pretrained semantic space (e.g., a set of word embeddings). We formulate the problem in such a way that we model each document as a Gaussian distribution in the word vector space. We design a generative model that combines both words and links in a consistent way. Leveraging the variance of a document allows us to model the uncertainty related to word and link generation. In most cases, our method outperforms state-of-the-art methods when using our document vectors as features for usual downstream tasks. In particular, GELD achieves better accuracy in classification and link prediction on Cora and Dblp. In addition, we demonstrate qualitatively the convenience of several properties of our method. We provide the implementation of GELD and the evaluation datasets to the community (https://github.com/AntoineGourru/DNEmbedding).
Fichier principal
Vignette du fichier
IJCAI2020_GELD__Copy_.pdf (441.55 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03343904 , version 1 (02-03-2022)

Identifiants

  • HAL Id : hal-03343904 , version 1

Citer

Antoine Gourru, Julien Velcin, Julien Jacques. Gaussian Embedding of Linked Documents from a Pretrained Semantic Space. Twenty-Ninth International Joint Conference on Artificial Intelligence (IJCAI-20), Jan 2021, Yokohama (virtual), Japan. ⟨hal-03343904⟩
52 Consultations
40 Téléchargements

Partager

Gmail Facebook X LinkedIn More