AGILe lemmatizer for Ancient Greek - Revision history

SilviaStopponi: updated people involved

2025-07-10T13:15:31Z

updated people involved

← Older revision		Revision as of 14:15, 10 July 2025
Line 10:		Line 10:
	* Silvia Stopponi		* Silvia Stopponi
	* Saskia Peels-Matthey		* Saskia Peels-Matthey
	* Malvina Nissim

	==Description==		==Description==

SilviaStopponi at 13:28, 24 November 2023

2023-11-24T13:28:58Z

← Older revision		Revision as of 14:28, 24 November 2023
Line 13:		Line 13:

	==Description==		==Description==
	AGILe is the first lemmatizer trained on Ancient Greek inscriptions. It is based on the [https://stanfordnlp.github.io/stanza/lemma.html Stanza lemmatizer] and the core of its trainig data is the [[Collection of Greek Ritual Norms]] (CGRN) corpus, complemented with data from the [[Pragmatic Resources in Old Indo-European Languages\|PROIEL]] corpus to increase the quantity of training data.		AGILe is the first lemmatizer trained on Ancient Greek inscriptions. It is based on the [https://stanfordnlp.github.io/stanza/lemma.html Stanza lemmatizer] by Qi et al. (2020) and the core of its trainig data is the [[Collection of Greek Ritual Norms]] (CGRN) corpus, complemented with data from the [[Pragmatic Resources in Old Indo-European Languages\|PROIEL]] corpus to increase the quantity of training data.

	AGILe achieved an accuracy of 85.1% on the CGRN test set, this means that it was able to correctly lemmatize 85.1% of the wordforms in the CGRN test set.		AGILe achieved an accuracy of 85.1% on the CGRN test set, this means that it was able to correctly lemmatize 85.1% of the wordforms in the CGRN test set.

SilviaStopponi at 21:27, 22 November 2023

2023-11-22T21:27:27Z

← Older revision		Revision as of 22:27, 22 November 2023
Line 3:		Line 3:

	==Authors==		==Authors==
	~~Creator~~ of the first version:		Developer of the first version:
	* Jasper Bos		* Jasper Bos

SilviaStopponi: added info and improved links

2023-11-22T21:27:01Z

added info and improved links

← Older revision		Revision as of 22:27, 22 November 2023
Line 10:		Line 10:
	* Silvia Stopponi		* Silvia Stopponi
	* Saskia Peels-Matthey		* Saskia Peels-Matthey
			* Malvina Nissim

	==Description==		==Description==
	AGILe is the first lemmatizer trained on Ancient Greek inscriptions. It is based on the [~~[Stanza lemmatizer\|~~https://stanfordnlp.github.io/stanza/lemma.html]] and the core of its trainig data is the [[Collection of Greek Ritual Norms]] (CGRN) corpus, complemented with data from the [[Pragmatic Resources in Old Indo-European Languages\|~~PROEIL~~]] corpus to increase the quantity of training data.		AGILe is the first lemmatizer trained on Ancient Greek inscriptions. It is based on the [https://stanfordnlp.github.io/stanza/lemma.html Stanza lemmatizer] and the core of its trainig data is the [[Collection of Greek Ritual Norms]] (CGRN) corpus, complemented with data from the [[Pragmatic Resources in Old Indo-European Languages\|PROIEL]] corpus to increase the quantity of training data.

	AGILe achieved an accuracy of 85.1% on the CGRN test set, this means that it was able to correctly lemmatize 85.1% of the wordforms in the CGRN test set.		AGILe achieved an accuracy of 85.1% on the CGRN test set, this means that it was able to correctly lemmatize 85.1% of the wordforms in the CGRN test set.

			AGILe accepts as input a string of text and returns a [https://stanfordnlp.github.io/stanza/data_objects.html#document Stanza Document] object.

	==References==		==References==

SilviaStopponi: modified authors

2023-11-21T16:22:00Z

modified authors

← Older revision		Revision as of 17:22, 21 November 2023
Line 6:		Line 6:
	* Jasper Bos		* Jasper Bos

	~~Maintainers~~:		People permanently involved:
	* Evelien de Graaf		* Evelien de Graaf
	* Silvia Stopponi		* Silvia Stopponi
			* Saskia Peels-Matthey

	==Description==		==Description==

SilviaStopponi: page created and added main information

2023-11-21T16:20:32Z

page created and added main information

New page

==Available==
* https://github.com/agile-gronlp/

==Authors==
Creator of the first version:
* Jasper Bos

Maintainers:
* Evelien de Graaf
* Silvia Stopponi

==Description==
AGILe is the first lemmatizer trained on Ancient Greek inscriptions. It is based on the [[Stanza lemmatizer|https://stanfordnlp.github.io/stanza/lemma.html]] and the core of its trainig data is the [[Collection of Greek Ritual Norms]] (CGRN) corpus, complemented with data from the [[Pragmatic Resources in Old Indo-European Languages|PROEIL]] corpus to increase the quantity of training data.

AGILe achieved an accuracy of 85.1% on the CGRN test set, this means that it was able to correctly lemmatize 85.1% of the wordforms in the CGRN test set.

==References==
de Graaf, E., Stopponi, S., Bos, J., Peels-Matthey, S., & Nissim, M. (2022, June). AGILe: The first lemmatizer for Ancient Greek inscriptions. In The 13th Conference on Language Resources and Evaluation (pp. 5334-5344). European Language Resources Association (ELRA). Available: https://aclanthology.org/2022.lrec-1.571/

Qi, P., Zhang, Y., Zhang, Y., Bolton, J., & Manning, C. D. (2020). Stanza: A Python natural language processing toolkit for many human languages. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (pp. 101–108). Association for Computational Linguistics. Available: https://aclanthology.org/2020.acl-demos.14.pdf

[[Category:Tools]] [[Category:Projects]] [[Category:Lemmatisation]] [[Category:Machine learning]] [[Category:Epigraphy]] [[Category:NLP]] [[Category:Openaccess]]