Method of noun phrase detection in Ukrainian texts

TL;DR

This paper proposes a new method for detecting noun phrases in Ukrainian texts using Universal Dependencies and named-entity recognition, validated on Ukrainian news corpus, improving accuracy for NLP preprocessing tasks.

Contribution

The paper introduces a complex noun phrase detection method for Ukrainian texts leveraging Universal Dependencies and named-entity recognition, addressing language-specific challenges.

Findings

Method achieves measurable accuracy improvements.

Universal Dependencies effectively represent sentence structure.

Potential for further accuracy enhancement with specialized NER models.

Abstract

Introduction. The area of natural language processing considers AI-complete tasks that cannot be solved using traditional algorithmic actions. Such tasks are commonly implemented with the usage of machine learning methodology and means of computer linguistics. One of the preprocessing tasks of a text is the search of noun phrases. The accuracy of this task has implications for the effectiveness of many other tasks in the area of natural language processing. In spite of the active development of research in the area of natural language processing, the investigation of the search for noun phrases within Ukrainian texts are still at an early stage. Results. The different methods of noun phrases detection have been analyzed. The expediency of the representation of sentences as a tree structure has been justified. The key disadvantage of many methods of noun phrase detection is the severe dependence of the effectiveness of their detection from the features of a certain language. Taking into account the unified format of sentence processing and the availability of the trained model for the building of sentence trees for Ukrainian texts, the Universal Dependency model has been chosen. The complex method of noun phrases detection in Ukrainian texts utilizing Universal Dependencies means and named-entity recognition model has been suggested. Experimental verification of the effectiveness of the suggested method on the corpus of Ukrainian news has been performed. Different metrics of method accuracy have been calculated. Conclusions. The results obtained can indicate that the suggested method can be used to find noun phrases in Ukrainian texts. An accuracy increase of the method can be made with the usage of appropriate named-entity recognition models according to a subject area.