Comparing explicit and predictive distributional semantic models endowed with syntactic contexts

Original Paper

DOI: 10.1007/s10579-016-9357-4

Cite this article as:
Gamallo, P. Lang Resources & Evaluation (2016). doi:10.1007/s10579-016-9357-4

Abstract

In this article, we introduce an explicit count-based strategy to build word space models with syntactic contexts (dependencies). A filtering method is defined to reduce explicit word-context vectors. This traditional strategy is compared with a neural embedding (predictive) model also based on syntactic dependencies. The comparison was performed using the same parsed corpus for both models. Besides, the dependency-based methods are also compared with bag-of-words strategies, both count-based and predictive ones. The results show that our traditional count-based model with syntactic dependencies outperforms other strategies, including dependency-based embeddings, but just for the tasks focused on discovering similarity between words with the same function (i.e. near-synonyms).

Keywords

Word similarity Word embeddings Count-based models Dependency-based semantic models 

Copyright information

© Springer Science+Business Media Dordrecht 2016

Authors and Affiliations

  1. 1.Centro de Investigación en Tecnoloxías da Información (CITIUS) Campus Vida Universidade de Santiago de CompostelaSantiago de CompostelaSpain

Personalised recommendations