Document Network Embedding: Coping for Missing Content and Missing Links - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2020

Document Network Embedding: Coping for Missing Content and Missing Links

Jean Dupuy
  • Fonction : Auteur
  • PersonId : 183418
  • IdHAL : jean-dupuy

Résumé

Searching through networks of documents is an important task. A promising path to improve the performance of information retrieval systems in this context is to leverage dense node and content representations learned with embedding techniques. However, these techniques cannot learn representations for documents that are either isolated or whose content is missing. To tackle this issue, assuming that the topology of the network and the content of the documents correlate, we propose to estimate the missing node representations from the available content representations, and conversely. Inspired by recent advances in machine translation, we detail in this paper how to learn a linear transformation from a set of aligned content and node representations. The projection matrix is efficiently calculated in terms of the singular value decomposition. The usefulness of the proposed method is highlighted by the improved ability to predict the neighborhood of nodes whose links are unobserved based on the projected content representations, and to retrieve similar documents when content is missing, based on the projected node representations.

Dates et versions

hal-02516908 , version 1 (24-03-2020)

Identifiants

Citer

Jean Dupuy, Adrien Guille, Julien Jacques. Document Network Embedding: Coping for Missing Content and Missing Links. 2020. ⟨hal-02516908⟩
18 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More