Evaluation of Distributional Semantic Models of Ancient Greek: Ancient Language Processing. Stopponi, S., Pedrazzini, N., Peels-Matthey, S., McGillivray, B., & Nissim, M. Proceedings of the Ancient Language Processing Workshop, September, 2023. Place: Varna, Bulgaria Publisher: Association for Computational Linguistics (ACL)![Evaluation of Distributional Semantic Models of Ancient Greek: Ancient Language Processing [pdf]](https://bibbase.org/img/filetypes/pdf.svg "pdf")
Paper abstract bibtex We evaluate four count-based and predictive distributional semantic models of Ancient Greek against AGREE, a composite benchmark of human judgements, to assess their ability to retrieve semantic relatedness. On the basis of the observations deriving from the analysis of the results, we design a procedure for a largerscale intrinsic evaluation of count-based and predictive language models, including syntactic embeddings. We also propose possible ways of exploiting the different layers of the whole AGREE benchmark (including both humanand machine-generated data) and different evaluation metrics.
@article{stopponi_evaluation_2023,
title = {Evaluation of {Distributional} {Semantic} {Models} of {Ancient} {Greek}: {Ancient} {Language} {Processing}},
shorttitle = {Evaluation of {Distributional} {Semantic} {Models} of {Ancient} {Greek}},
url = {https://pure.rug.nl/ws/portalfiles/portal/777728242/stopponi_et_al_2023_alp.pdf},
abstract = {We evaluate four count-based and predictive distributional semantic models of Ancient Greek against AGREE, a composite benchmark of human judgements, to assess their ability to retrieve semantic relatedness. On the basis of the observations deriving from the analysis of the results, we design a procedure for a largerscale intrinsic evaluation of count-based and predictive language models, including syntactic embeddings. We also propose possible ways of exploiting the different layers of the whole AGREE benchmark (including both humanand machine-generated data) and different evaluation metrics.},
journal = {Proceedings of the Ancient Language Processing Workshop},
author = {Stopponi, Silvia and Pedrazzini, Nilo and Peels-Matthey, Saskia and McGillivray, Barbara and Nissim, Malvina},
month = sep,
year = {2023},
note = {Place: Varna, Bulgaria
Publisher: Association for Computational Linguistics (ACL)},
keywords = {ancient greek, ancient languages, benchmark, evaluation, languge models, natural language processing, word2vec},
pages = {49--58},
}