Other formats:
BibTeX
LaTeX
RIS
@inproceedings{2361461, author = {Denisová, Michaela and Rychlý, Pavel}, address = {Karlova Studánka}, booktitle = {Proceedings of the Seventeenth Workshop on Recent Advances in Slavonic Natural Languages Processing, RASLAN 2023}, editor = {Aleš Horák, Pavel Rychlý, Adam Rambousek}, keywords = {Cross-lingual word embeddings; Bilingual lexicon induction; Evaluation dataset’s size}, howpublished = {tištěná verze "print"}, language = {eng}, location = {Karlova Studánka}, isbn = {978-80-263-1793-7}, pages = {47-56}, publisher = {Tribun EU}, title = {Does Size Matter? - Comparing Evaluation Dataset Size for the Bilingual Lexicon Induction}, url = {https://raslan2022.nlp-consulting.net/}, year = {2023} }
TY - JOUR ID - 2361461 AU - Denisová, Michaela - Rychlý, Pavel PY - 2023 TI - Does Size Matter? - Comparing Evaluation Dataset Size for the Bilingual Lexicon Induction PB - Tribun EU CY - Karlova Studánka SN - 9788026317937 KW - Cross-lingual word embeddings KW - Bilingual lexicon induction KW - Evaluation dataset’s size UR - https://raslan2022.nlp-consulting.net/ N2 - Cross-lingual word embeddings have been a popular approach for inducing bilingual lexicons. However, the evaluation of this task varies from paper to paper, and gold standard dictionaries used for the evaluation are frequently criticised for occurring mistakes. Although there have been efforts to unify the evaluation and gold standard dictionaries, we propose a new property that should be considered when compiling an evaluation dataset: size. In this paper, we evaluate three baseline models on three diverse language pairs (Estonian-Slovak, Czech-Slovak, English-Korean) and experiment with evaluation datasets of various sizes: 200, 500, 1.5K, and 3K source words. Moreover, we compare the results with manual error analysis. In this experiment, we show whether the size of an evaluation dataset impacts the results and how to select the ideal evaluation dataset size. We make our code and datasets publicly available. ER -
DENISOVÁ, Michaela and Pavel RYCHLÝ. Does Size Matter? - Comparing Evaluation Dataset Size for the Bilingual Lexicon Induction. In Aleš Horák, Pavel Rychlý, Adam Rambousek. \textit{Proceedings of the Seventeenth Workshop on Recent Advances in Slavonic Natural Languages Processing, RASLAN 2023}. Karlova Studánka: Tribun EU, 2023, p.~47-56. ISBN~978-80-263-1793-7.
|