Extracting domain-specific terms using contextual word embeddings

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Repar, Andraž, Lavrač, Nada, Pollak, Senja
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929729180794880
author Repar, Andraž
Lavrač, Nada
Pollak, Senja
author_facet Repar, Andraž
Lavrač, Nada
Pollak, Senja
contents Automated terminology extraction refers to the task of extracting meaningful terms from domain-specific texts. This paper proposes a novel machine learning approach to terminology extraction, which combines features from traditional term extraction systems with novel contextual features derived from contextual word embeddings. Instead of using a predefined list of part-of-speech patterns, we first analyse a new term-annotated corpus RSDO5 for the Slovenian language and devise a set of rules for term candidate selection and then generate statistical, linguistic and context-based features. We use a support-vector machine algorithm to train a classification model, evaluate it on the four domains (biomechanics, linguistics, chemistry, veterinary) of the RSDO5 corpus and compare the results with state-of-art term extraction approaches for the Slovenian language. Our approach provides significant improvements in terms of F1 score over the previous state-of-the-art, which proves that contextual word embeddings are valuable for improving term extraction.
format Preprint
id arxiv_https___arxiv_org_abs_2502_17278
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Extracting domain-specific terms using contextual word embeddings
Repar, Andraž
Lavrač, Nada
Pollak, Senja
Computation and Language
Automated terminology extraction refers to the task of extracting meaningful terms from domain-specific texts. This paper proposes a novel machine learning approach to terminology extraction, which combines features from traditional term extraction systems with novel contextual features derived from contextual word embeddings. Instead of using a predefined list of part-of-speech patterns, we first analyse a new term-annotated corpus RSDO5 for the Slovenian language and devise a set of rules for term candidate selection and then generate statistical, linguistic and context-based features. We use a support-vector machine algorithm to train a classification model, evaluate it on the four domains (biomechanics, linguistics, chemistry, veterinary) of the RSDO5 corpus and compare the results with state-of-art term extraction approaches for the Slovenian language. Our approach provides significant improvements in terms of F1 score over the previous state-of-the-art, which proves that contextual word embeddings are valuable for improving term extraction.
title Extracting domain-specific terms using contextual word embeddings
topic Computation and Language
url https://arxiv.org/abs/2502.17278