Task-specific dependency-based word embedding methods

Abstract

While most traditional word embedding methods target generic tasks, two task-specific dependency-based word embedding methods are proposed for better performance in text classification tasks in this work. First, we exploit the dependency parsing tree structure to capture the structural information of a sentence, and develop a method called dependency-based word embedding (DWE). It finds keywords and neighbor words of a target word as contexts via dependency parsing. Next, we leverage the word-class co-occurrence statistics to model the class distributional information and incorporate it into the embedding learning process. This leads to the class-enhanced dependency-based word embedding (CEDWE) method. Task-specific corpora and the matrix-factorization-based framework are used to train DWE and CEDWE. Seven text classification datasets are used to evaluate the performance of DWE and CEDWE, and experimental results show that they outperform several state-of-the-art word embedding methods.