Modeling linking between text and lexicon with OntoLex-Lemon: a case study of computational terminology for the Babylonian Talmud

What it is about

The paper reports the first steps of a computational terminology for the Babylonian Talmud, built for an Italian translation project. About 4,000 candidate terms were extracted from the translated treatises with the T2K tool. Terms with high tf-idf (specific to few treatises, unlike the frequent "rabbi") were kept and checked by domain experts, and the data were exported as OntoLex-Lemon lexical entries. The author uses the FrAC module of OntoLex for absolute frequency, tf-idf values and attestations, each attestation pointing to a passage (Berakhot, for example) and carrying its quotation. The worked example is the term shemà, with a frequency of 206, a tf-idf of about 0.020 and three attested passages. Linking terms back to the text is still manual, through an editor under development, and the untranslated Hebrew text is not yet linked. The paper reports no evaluation figures.

Ideas

• I1. Term selection by tf-idf across treatises: rank candidate terms by tf-idf over tractates, drop terms spread across most of them, and send the rest to a human check. In world, this gives a deterministic list of the characteristic terms of a tractate, with the rule written out.
• I2. Attestation as a record: store each attested passage id with its quotation and the term frequency, so that a term can say where it comes from. This fits the explain-why rule of prag and world: an answer can point to its attestations.
• I3. Lexical-linking test: build a small gold set of token-to-entry links (a word in a verse linked to its lexicon entry, as in the shemà example) and measure the lemma output of tools/hbo against it. The paper has no measures, so this set is the part Mova can add.

For Mova

I1 goes into world and The lexicon. I2 goes into world, with the passage ids of languages/tmr/ (Babylonian Talmudic Aramaic) as its first use. I3 is a test set for tools/hbo and is recorded in The lexicon.

Cite

The paper itself, not this card. BibTeX from the library's record of the work. DOI 10.63317/4ggop97xxayu

@inproceedings{sciolette2024modeling,
  title = {{Modeling linking between text and lexicon with OntoLex-Lemon: a case study of computational terminology for the Babylonian Talmud}},
  author = {Sciolette, Flavia},
  booktitle = {Proceedings of the 9th Workshop on Linked Data in Linguistics @ LREC-COLING 2024},
  year = {2024},
  doi = {10.63317/4ggop97xxayu},
  url = {https://doi.org/10.63317/4ggop97xxayu}
}

References

22 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Hamed Babaei Giglou, Jennifer D’Souza, and Sören Auer. 2023. LLMs4OL: Large language models for ontology learning. page 408–427, Berlin, Heidelberg. Springer-Verlag. find
2. Andrea Bellandi, Emiliano Giovannetti, Simone Marchi, Silvia Piccini, and Flavia Sciolette. 2020. Come dare senso a un termine? caratteristiche, potenzialità e opportunità dello strumento Lexo. In Comunicazione al XXX Convegno Ass.I.Term., Eurac Research, Bolzano. find
3. Christian Bizer, Tom Heath, and Tim Berners-Lee. 2023. Linked data – the story so far. In Linking the World’s Information: Essays on Tim Berners-Lee’s Invention of the World Wide Web, pages 115–143. Association for Computing Machinery, New York, NY, United States. ↗
4. Paul Buitelaar, Philippe Cimiano, and Bernardo Magnini. 2005. Ontology learning from text: An overview. In Ontology Learning from Text: Methods, Evaluation and Applications. IOS Press, Amsterdam. find
5. Christian Chiarcos, Elena-Simona Apostol, Besim Kabashi, and Ciprian-Octavian Truică. 2022. Modelling frequency, attestation, and corpus-based information with OntoLex-FrAC. In Proceedings of the 29th International Conference on Computational Linguistics, pages 4018–4027, Gyeongju, Republic of Korea. find
6. Elena Chiocchetti and Natascia Ralli. 2022. Introduzione. In Risorse e strumenti per l’elaborazione e la diffusione della terminologia in Italia. Eurac Research, Bolzano. find
7. Philipp Cimiano, Christian Chiarcos, John P. Mc-Crae, and Jorge Gracia. 2020. Linguistic linked data in digital humanities. In Linguistic Linked Data in Digital Humanities, pages 229–262. Springer International Publishing, Cham. knowledge from texts. In Proceedings of 9th Edition of International Conference on Language Resources and Evaluation, pages 178–190, Reykjavik. ACL. ↗
8. Emiliano Giovannetti, Davide Albanesi, Andrea Bellandi, David Dattilo, Angelo Maria Del Grosso, and Simone Marchi. 2021. An ontology of masters of the Babylonian Talmud. Digital Scholarship in the Humanities, fqab043. ↗
9. Emiliano Giovannetti, Andrea Bellandi, David Dattilo, Angelo Maria Del Grosso, Simone Marchi, Alessandra Pecchioli, and Silvia Piccini. 2020. The terminology of the Babylonian Talmud: Extraction, representation and use in the context of computational linguistics. Materia Giudaica, XXV. find
10. Annette Klosa. 2015. On corpus citations in monolingual general dictionaries. Dictionaries: Journal of the Dictionary Society of North America, 36(1):72–87. ↗
11. Yiheng Liu, Tianle Han, Siyuan Ma, Jiayue Zhang, Yuanyuan Yang, Jiaming Tian, Hao He, Antong Li, Mengshen He, Zhengliang Liu, Zihao Wu, Lin Zhao, Dajiang Zhu, Xiang Li, Ning Qiang, Dingang Shen, Tianming Liu, and Bao Ge. 2023. Summary of ChatGPT-related research and perspective towards the future of large language models. Meta-Radiology, 1(2):100017. Simone. ↗
12. Marchi, Marianna Colombo, David Dattilo, and Emiliano Giovannetti. 2022. Un esperimento di visualizzazione grafica della terminologia del Talmud Babilonese. In AIUCD 2022 - Proceedings, Lecce, Italy. find
13. John P. McCrae, Julia Bosque-Gil, Jorge Gracia, Paul Buitelaar, and Philipp Cimiano. 2017. The OntoLex-Lemon model: development and applications. In Proceedings of eLex 2017 conference, pages 19–21. find
14. Simon Meoni, Eric De la Clergerie, and Theo Ryffel. 2023. Large language models as instructors: A study on multilingual clinical entity extraction. In The 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks, pages 178–190, Toronto, Canada. Association for Computational Linguistics. ↗
15. Fabian Neuhaus. 2023. Ontologies in the era of large language models: a perspective. Applied Ontology, 18(4):399–407. ↗
16. Alessandra Pecchioli, Davide Albanesi, Andrea Bellandi, Emiliano Giovannetti, and Simone Marchi. 2018. Annotazione linguistica automatica dell’ebraico mishnaico: Esperimenti sul Talmud Babilonese. Materia Giudaica, XXIII. find
17. Nathaniel Robinson, Perez Ogayo, David R. Mortensen, and Graham Neubig. 2023. Chat-GPT MT: Competitive for high- (but not low-) resource languages. In Proceedings of the Eighth Conference on Machine Translation, pages 392– 418, Singapore. Association for Computational Linguistics. find
18. Ana Salgado, Rute Costa, and Toma Tasovac. 2022. Applying Terminological Methods to Lexicographic Work: Terms and Their Domains. In Dictionaries and Society. Proceedings of the XX EURALEX International Congress, pages 181– 195, Mannheim. IDS-Verlag. find
19. Davide Saponaro, Emiliano Giovannetti, and Flavia Sciolette. 2022. From religious sources to computational resources: Approach and case study on hebrew terms and concepts. Materia Giudaica, 27. find
20. Michael L. Satlow and Michael Sperling. 2022. The rabbinic citation network. AJS Review: The Journal of the Association for Jewish Studies, 46(2):291–319. ↗
21. Marcello Soffritti. 2010. Termontografia e innovazione della terminologia plurilingue. In Franco Bertaccini, Sara Castagnoli, and Francesco La Forgia, editors, Terminologia a colori, pages 31–5. Bononia University Press, Forlì. find
22. Mark D. Wilkinson, Michel Dumontier, I Jsbrand Jan Aalbersberg, Gabriel Appleton, Myles Axton, Arie Baak, and Niklas Blomberg. 2016. The FAIR guiding principles for scientific data management and stewardship. Scientific data, 3. ↗

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/aclbulk-2024-sciolette-modeling-linking-between-text-lexicon/