TermEnsembler

An ensemble learning approach to bilingual term extraction and alignment

Bibliographic Data

ID20395196
AuthorsAndraž Repar (0000-0001-9664-6145, Jožef Stefan Institute), Vid Podpečan (0000-0002-7314-4529, Jožef Stefan Institute), Anže Vavpetič (Jožef Stefan Institute), Nada Lavrač (0000-0002-9995-7093, Jožef Stefan Institute), Senja Pollak (0000-0002-4380-0863, Jožef Stefan Institute)
Year2022
Pages93-120
Publication date2022-07-06
Open AccessYes
TypeARTICLE
VenueTerminology International Journal of Theoretical and Applied Issues in Specialized Communication (JOURNAL)
Journal identifiersISSN: 0929-9971 • E-ISSN: 1569-9994
PublisherJohn Benjamins Publishing Company (PUBLISHER • NL)
DOI10.1075/term.00029.rep
OpenAlexW2963848110
LanguageEN
Citations received2
References cited15

This paper describes TermEnsembler, a bilingual term extraction and alignment system utilizing a novel ensemble learning approach to bilingual term alignment. In the proposed system, the processing starts with monolingual term extraction from a language industry standard file type containing aligned English and Slovenian texts. The two separate term lists are then automatically aligned using an ensemble of seven bilingual alignment methods, which are first executed separately and then merged using the weights learned with an evolutionary algorithm. In the experiments, the weights were learned on one domain and tested on two other domains. When evaluated on the top 400 aligned term pairs, the precision of term alignment is over 96%, while the number of correctly aligned multi-word unit terms exceeds 30% when evaluated on the top 400 term pairs

Natural language processing · Biomedical Text Mining and Ontologies · Computer Science · Mathematics · Natural Language Processing Techniques · Topic Modeling · Artificial Intelligence

Tools

Open DOIOpen Access