Syntactic and semantic classification of verb arguments using dependency-based and rich semantic features

TL;DR

This paper presents a supervised machine-learning approach for CPA parsing that combines syntactic and semantic features, achieving improved accuracy in classifying verb arguments despite data sparsity.

Contribution

It introduces a novel combination of dependency-based syntactic features and rich semantic features from WordNet and embeddings for CPA parsing.

Findings

The approach outperforms other systems by about 4% in F-score.

Combining syntactic and semantic features improves classification accuracy.

The method remains effective despite data sparsity issues.

Abstract

Corpus Pattern Analysis (CPA) has been the topic of Semeval 2015 Task 15, aimed at producing a system that can aid lexicographers in their efforts to build a dictionary of meanings for English verbs using the CPA annotation process. CPA parsing is one of the subtasks which this annotation process is made of and it is the focus of this report. A supervised machine-learning approach has been implemented, in which syntactic features derived from parse trees and semantic features derived from WordNet and word embeddings are used. It is shown that this approach performs well, even with the data sparsity issues that characterize the dataset, and can obtain better results than other system by a margin of about 4% f-score.