Fusing Document, Collection and Label Graph-based Representations with Word Embeddings for Text Classification

Konstantinos Skianis (1) , Fragkiskos Malliaros (2, 3) , Michalis Vazirgiannis (1)

1 LIX - Laboratoire d'informatique de l'École polytechnique [Palaiseau]
2 CVN - Centre de vision numérique
3 GALEN-POST - Organ Modeling through Extraction, Representation and Understanding of Medical Image Content

Contrary to the traditional Bag-of-Words approach, we consider the Graph-of-Words (GoW) model in which each document is represented by a graph that encodes relationships between the different terms. Based on this formulation, the importance of a term is determined by weighting the corresponding node in the document, collection and label graphs, using node centrality criteria. We also introduce novel graph-based weighting schemes by enriching graphs with word-embedding similarities, in order to reward or penalize semantic relationships. Our methods produce more discriminative feature weights for text categorization, out-performing existing frequency-based criteria.

Domains: Computer Science [cs]; Machine Learning [cs.LG]; Computer Science [cs]; Artificial Intelligence [cs.AI]; Computer Science [cs]; Document and Text Processing

Konstantinos Skianis, Fragkiskos Malliaros, Michalis Vazirgiannis. Fusing Document, Collection and Label Graph-based Representations with Word Embeddings for Text Classification. NAACL-HLT Workshop on Graph-Based Natural Language Processing (TextGraphs), Jun 2018, New Orleans, Louisiana, United States. ⟨10.18653/v1/w18-1707⟩. ⟨hal-01848880⟩