UnibucKernel: A kernel-based learning method for complex word identification

TL;DR

This paper introduces UnibucKernel, a kernel-based learning method combining low-level and high-level features for complex word identification, achieving competitive results in shared tasks.

Contribution

The paper presents a novel kernel-based approach that integrates multiple feature types for complex word identification, improving upon previous methods.

Findings

Achieved third place in the 2018 CWI Shared Task on Wikipedia data.

Reported improved results beyond the competition.

Demonstrated effectiveness of combining semantic and character features.

Abstract

In this paper, we present a kernel-based learning approach for the 2018 Complex Word Identification (CWI) Shared Task. Our approach is based on combining multiple low-level features, such as character n-grams, with high-level semantic features that are either automatically learned using word embeddings or extracted from a lexical knowledge base, namely WordNet. After feature extraction, we employ a kernel method for the learning phase. The feature matrix is first transformed into a normalized kernel matrix. For the binary classification task (simple versus complex), we employ Support Vector Machines. For the regression task, in which we have to predict the complexity level of a word (a word is more complex if it is labeled as complex by more annotators), we employ v-Support Vector Regression. We applied our approach only on the three English data sets containing documents from Wikipedia, WikiNews and News domains. Our best result during the competition was the third place on the English Wikipedia data set. However, in this paper, we also report better post-competition results.