Další formáty:
BibTeX
LaTeX
RIS
@inproceedings{2295462, author = {Denisová, Michaela and Rychlý, Pavel}, address = {Brno}, booktitle = {Electronic lexicography in the 21st century (eLex 2023): Invisible Lexicography. Proceedings of the eLex 2023 conference}, keywords = {cross-lingual embedding models; bilingual lexicon induction task; retrieving translation equivalents; evaluation}, howpublished = {tištěná verze "print"}, language = {eng}, location = {Brno}, pages = {1-18}, publisher = {Lexical Computing CZ s.r.o.}, title = {Evaluation of the Cross-lingual Embedding Models from the Lexicographic Perspective}, url = {https://elex.link/elex2023/wp-content/uploads/elex2023_proceedings.pdf#page=9}, year = {2023} }
TY - JOUR ID - 2295462 AU - Denisová, Michaela - Rychlý, Pavel PY - 2023 TI - Evaluation of the Cross-lingual Embedding Models from the Lexicographic Perspective PB - Lexical Computing CZ s.r.o. CY - Brno KW - cross-lingual embedding models KW - bilingual lexicon induction task KW - retrieving translation equivalents KW - evaluation UR - https://elex.link/elex2023/wp-content/uploads/elex2023_proceedings.pdf#page=9 N2 - Cross-lingual embedding models (CMs) enable us to transfer lexical knowledge across languages. Therefore, they represent a useful approach for retrieving translation equivalents in lexicography. However, these models have been mainly oriented towards the natural language processing (NLP) field, lacking proper evaluation with error evaluation datasets that were compiled automatically. This causes discrepancies between models hindering the correct interpretation of the results. In this paper, we aim to address these issues and make these models more accessible for lexicography by evaluating them from a lexicographic point of view. We evaluate three benchmark CMs on three diverse language pairs: close, distant, and different script languages. Additionally, we propose key parameters that the evaluation dataset should include to meet lexicographic needs, have reproducible results, accurately reflect the performance, and set appropriate parameters during training. Our code and evaluation datasets are publicly available. ER -
DENISOVÁ, Michaela a Pavel RYCHLÝ. Evaluation of the Cross-lingual Embedding Models from the Lexicographic Perspective. In \textit{Electronic lexicography in the 21st century (eLex 2023): Invisible Lexicography. Proceedings of the eLex 2023 conference}. Brno: Lexical Computing CZ s.r.o., 2023, s.~1-18. ISSN~2533-5626.
|