Syntactic and semantic classification of verb arguments using dependency-based and rich semantic features
This work aids lexicographers in building dictionaries by automating part of the annotation process, but it is incremental as it builds on existing methods for a specific NLP task.
The paper tackled the problem of parsing verb arguments for Corpus Pattern Analysis using a supervised machine-learning approach with syntactic and semantic features, achieving a 4% f-score improvement over other systems despite data sparsity.
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.