Evaluating automatic sentence alignment approaches on English-Slovak sentences
Abstract Parallel texts represent a very valuable resource in many applications of natural language processing. The fundamental step in creating parallel corpus is the alignment. Sentence alignment is the issue of finding correspondence between source sentences and their equivalent translations in t...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-11-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-47479-w |
| _version_ | 1827711428712202240 |
|---|---|
| author | Frantisek Forgac Dasa Munkova Michal Munk Livia Kelebercova |
| author_facet | Frantisek Forgac Dasa Munkova Michal Munk Livia Kelebercova |
| author_sort | Frantisek Forgac |
| collection | DOAJ |
| description | Abstract Parallel texts represent a very valuable resource in many applications of natural language processing. The fundamental step in creating parallel corpus is the alignment. Sentence alignment is the issue of finding correspondence between source sentences and their equivalent translations in the target text. A number of automatic sentence alignment approaches were proposed including neural networks, which can be divided into length-based, lexicon-based, and translation-based. In our study, we used five different aligners, namely Bilingual sentence aligner (BSA), Hunalign, Bleualign, Vecalign, and Bertalign. We evaluated both, the performance of the Bertalign in terms of accuracy against the up to now employed aligners as well as among each other in the language pair English-Sovak. We created our custom corpus consisting of texts collected in 2021 and 2022. Vecalign and Bertalign performed statistically significantly best and BSA the worst. Hunalign and Bleualign achieved the same performance in terms of F1 score. However, Bleualign achieved the most diverse results in terms of performance. |
| first_indexed | 2024-03-10T17:55:31Z |
| format | Article |
| id | doaj.art-0693716c6dec4b8f95412f786d596a0a |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-03-10T17:55:31Z |
| publishDate | 2023-11-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-0693716c6dec4b8f95412f786d596a0a2023-11-20T09:12:36ZengNature PortfolioScientific Reports2045-23222023-11-0113111210.1038/s41598-023-47479-wEvaluating automatic sentence alignment approaches on English-Slovak sentencesFrantisek Forgac0Dasa Munkova1Michal Munk2Livia Kelebercova3Faculty of Natural Sciences and Informatics, Constantine the Philosopher University in NitraFaculty of Natural Sciences and Informatics, Constantine the Philosopher University in NitraFaculty of Natural Sciences and Informatics, Constantine the Philosopher University in NitraFaculty of Natural Sciences and Informatics, Constantine the Philosopher University in NitraAbstract Parallel texts represent a very valuable resource in many applications of natural language processing. The fundamental step in creating parallel corpus is the alignment. Sentence alignment is the issue of finding correspondence between source sentences and their equivalent translations in the target text. A number of automatic sentence alignment approaches were proposed including neural networks, which can be divided into length-based, lexicon-based, and translation-based. In our study, we used five different aligners, namely Bilingual sentence aligner (BSA), Hunalign, Bleualign, Vecalign, and Bertalign. We evaluated both, the performance of the Bertalign in terms of accuracy against the up to now employed aligners as well as among each other in the language pair English-Sovak. We created our custom corpus consisting of texts collected in 2021 and 2022. Vecalign and Bertalign performed statistically significantly best and BSA the worst. Hunalign and Bleualign achieved the same performance in terms of F1 score. However, Bleualign achieved the most diverse results in terms of performance.https://doi.org/10.1038/s41598-023-47479-w |
| spellingShingle | Frantisek Forgac Dasa Munkova Michal Munk Livia Kelebercova Evaluating automatic sentence alignment approaches on English-Slovak sentences Scientific Reports |
| title | Evaluating automatic sentence alignment approaches on English-Slovak sentences |
| title_full | Evaluating automatic sentence alignment approaches on English-Slovak sentences |
| title_fullStr | Evaluating automatic sentence alignment approaches on English-Slovak sentences |
| title_full_unstemmed | Evaluating automatic sentence alignment approaches on English-Slovak sentences |
| title_short | Evaluating automatic sentence alignment approaches on English-Slovak sentences |
| title_sort | evaluating automatic sentence alignment approaches on english slovak sentences |
| url | https://doi.org/10.1038/s41598-023-47479-w |
| work_keys_str_mv | AT frantisekforgac evaluatingautomaticsentencealignmentapproachesonenglishslovaksentences AT dasamunkova evaluatingautomaticsentencealignmentapproachesonenglishslovaksentences AT michalmunk evaluatingautomaticsentencealignmentapproachesonenglishslovaksentences AT liviakelebercova evaluatingautomaticsentencealignmentapproachesonenglishslovaksentences |