Named Entity Annotation Projection Applied to Classical Languages. Yousef, T., Palladino, C., Heyer, G., & Jänicke, S. Proceedings of the 7th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature, 2023. ![Named Entity Annotation Projection Applied to Classical Languages [pdf]](https://bibbase.org/img/filetypes/pdf.svg "pdf")
Paper abstract bibtex In this study, we demonstrate how to apply cross-lingual annotation projection to transfer named-entity annotations to classical languages for which limited or no resources and annotated texts are available, aiming to enrich their NER training datasets and train a model to perform NER tagging. Our approach employs sentence-level aligned corpora of ancient texts and the translation in a modern language, for which high-quality off-the-shelf NER systems are available. We automatically annotate the text of the modern language and employ a stateof-the-art neural word alignment system to find translation equivalents. Finally, we transfer the annotations to the corresponding tokens in the ancient texts using a direct projection heuristic. We applied our method to ancient Greek and Latin using the Bible with the English translation as a parallel corpus. We used the resulting annotations to enhance the performance of an existing NER model for ancient Greek.
@article{yousef_named_2023,
title = {Named {Entity} {Annotation} {Projection} {Applied} to {Classical} {Languages}},
url = {https://aclanthology.org/2023.latechclfl-1.19.pdf},
abstract = {In this study, we demonstrate how to apply cross-lingual annotation projection to transfer named-entity annotations to classical languages for which limited or no resources and annotated texts are available, aiming to enrich their NER training datasets and train a model to perform NER tagging. Our approach employs sentence-level aligned corpora of ancient texts and the translation in a modern language, for which high-quality off-the-shelf NER systems are available. We automatically annotate the text of the modern language and employ a stateof-the-art neural word alignment system to find translation equivalents. Finally, we transfer the annotations to the corresponding tokens in the ancient texts using a direct projection heuristic. We applied our method to ancient Greek and Latin using the Bible with the English translation as a parallel corpus. We used the resulting annotations to enhance the performance of an existing NER model for ancient Greek.},
language = {en},
journal = {Proceedings of the 7th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature},
author = {Yousef, Tariq and Palladino, Chiara and Heyer, Gerhard and Jänicke, Stefan},
year = {2023},
pages = {175--182},
}
Downloads: 0
{"_id":"YLExXd42SNdRuetG7","bibbaseid":"yousef-palladino-heyer-jnicke-namedentityannotationprojectionappliedtoclassicallanguages-2023","author_short":["Yousef, T.","Palladino, C.","Heyer, G.","Jänicke, S."],"bibdata":{"bibtype":"article","type":"article","title":"Named Entity Annotation Projection Applied to Classical Languages","url":"https://aclanthology.org/2023.latechclfl-1.19.pdf","abstract":"In this study, we demonstrate how to apply cross-lingual annotation projection to transfer named-entity annotations to classical languages for which limited or no resources and annotated texts are available, aiming to enrich their NER training datasets and train a model to perform NER tagging. Our approach employs sentence-level aligned corpora of ancient texts and the translation in a modern language, for which high-quality off-the-shelf NER systems are available. We automatically annotate the text of the modern language and employ a stateof-the-art neural word alignment system to find translation equivalents. Finally, we transfer the annotations to the corresponding tokens in the ancient texts using a direct projection heuristic. We applied our method to ancient Greek and Latin using the Bible with the English translation as a parallel corpus. We used the resulting annotations to enhance the performance of an existing NER model for ancient Greek.","language":"en","journal":"Proceedings of the 7th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature","author":[{"propositions":[],"lastnames":["Yousef"],"firstnames":["Tariq"],"suffixes":[]},{"propositions":[],"lastnames":["Palladino"],"firstnames":["Chiara"],"suffixes":[]},{"propositions":[],"lastnames":["Heyer"],"firstnames":["Gerhard"],"suffixes":[]},{"propositions":[],"lastnames":["Jänicke"],"firstnames":["Stefan"],"suffixes":[]}],"year":"2023","pages":"175–182","bibtex":"@article{yousef_named_2023,\n\ttitle = {Named {Entity} {Annotation} {Projection} {Applied} to {Classical} {Languages}},\n\turl = {https://aclanthology.org/2023.latechclfl-1.19.pdf},\n\tabstract = {In this study, we demonstrate how to apply cross-lingual annotation projection to transfer named-entity annotations to classical languages for which limited or no resources and annotated texts are available, aiming to enrich their NER training datasets and train a model to perform NER tagging. Our approach employs sentence-level aligned corpora of ancient texts and the translation in a modern language, for which high-quality off-the-shelf NER systems are available. We automatically annotate the text of the modern language and employ a stateof-the-art neural word alignment system to find translation equivalents. Finally, we transfer the annotations to the corresponding tokens in the ancient texts using a direct projection heuristic. We applied our method to ancient Greek and Latin using the Bible with the English translation as a parallel corpus. We used the resulting annotations to enhance the performance of an existing NER model for ancient Greek.},\n\tlanguage = {en},\n\tjournal = {Proceedings of the 7th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature},\n\tauthor = {Yousef, Tariq and Palladino, Chiara and Heyer, Gerhard and Jänicke, Stefan},\n\tyear = {2023},\n\tpages = {175--182},\n}\n\n\n\n","author_short":["Yousef, T.","Palladino, C.","Heyer, G.","Jänicke, S."],"key":"yousef_named_2023","id":"yousef_named_2023","bibbaseid":"yousef-palladino-heyer-jnicke-namedentityannotationprojectionappliedtoclassicallanguages-2023","role":"author","urls":{"Paper":"https://aclanthology.org/2023.latechclfl-1.19.pdf"},"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/zotero-group/schulzkx/5158478","dataSources":["JFDnASMkoQCjjGL8E"],"keywords":[],"search_terms":["named","entity","annotation","projection","applied","classical","languages","yousef","palladino","heyer","jänicke"],"title":"Named Entity Annotation Projection Applied to Classical Languages","year":2023}