Corpora Issues in Validation of Serbian Wordnet

Krstev, Cvetana; Pavlović-Lažetić, Gordana; Obradović, Ivan; Vitas, Duško

doi:10.1007/978-3-540-39398-6_19

Cited by 2 publications

(1 citation statement)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We used two bilingual lexical resources that we processed with the tool LeXimir . (a) Serbian Wordnet (SWN) (Krstev 2014), g which is aligned to the Princeton WordNet (PWN), and (b) a bilingual list containing general lexica with 10,551 English/Serbian entries. The production of the bilingual list of inflected forms was done in several steps: First, a parallel list from SWN and PWN containing 75,766 aligned English/Serbian single and multi-word literals was compiled.…”

Section: Lexical Resources and Toolsmentioning

confidence: 99%

Two approaches to compilation of bilingual multi-word terminology lists from lexical resources

Šandrih¹,

Krstev²,

Stanković³

2020

Nat. Lang. Eng.

Self Cite

View full text Add to dashboard Cite

In this paper, we present two approaches and the implemented system for bilingual terminology extraction that rely on an aligned bilingual domain corpus, a terminology extractor for a target language, and a tool for chunk alignment. The two approaches differ in the way terminology for the source language is obtained: the first relies on an existing domain terminology lexicon, while the second one uses a term extraction tool. For both approaches, four experiments were performed with two parameters being varied. In the experiments presented in this paper, the source language was English, and the target language Serbian, and a selected domain was Library and Information Science, for which an aligned corpus exists, as well as a bilingual terminological dictionary. For term extraction, we used the FlexiTerm tool for the source language and a shallow parser for the target language, while for word alignment we used GIZA++. The evaluation results show that for the first approach the F1 score varies from 29.43% to 51.15%, while for the second it varies from 61.03% to 71.03%. On the basis of the evaluation results, we developed a binary classifier that decides whether a candidate pair, composed of aligned source and target terms, is valid. We trained and evaluated different classifiers on a list of manually labeled candidate pairs obtained after the implementation of our extraction system. The best results in a fivefold cross-validation setting were achieved with the Radial Basis Function Support Vector Machine classifier, giving a F1 score of 82.09% and accuracy of 78.49%.

show abstract

Section: Lexical Resources and Toolsmentioning

confidence: 99%