Constructing an Annotated Resource for Part-Of-Speech Tagging of Mishnaic Hebrew

What it is about

The Babylonian Talmud Translation Project had no tagged Mishnaic Hebrew to train a stochastic POS tagger, so the team hand-tagged about 10,400 tokens of the Mishna inside their translation database. The annotation tool reuses earlier subtoken splits (stems, prefixes, suffixes) and proposes the most frequent past analysis. The tagset is their own, with about twenty labels, because the UD Hebrew tagset is too coarse and has no prefix tags. Each word gets two layers: a "category" (out of context) and a "function" (in context); only the function layer is used for training. Three off-the-shelf taggers (Stanford, HunPos, TreeTagger) were scored with 10-fold cross-validation: Stanford 87.9%, TreeTagger 86.7%, HunPos 86.3%. Lemmatisation and the Babylonian Aramaic of the Gemara are the stated next steps.

Ideas

• I1. Keep two parallel layers in the Mishnaic lexicon: a context-free category and an in-context function for each form. The parser then decides the function, and the lexicon still shows that a form such as a verb-or-adjective reading exists.
• I2. Give prefixes their own tags (preposition, conjunction, article, relative) inside tools/hbo segment output, and fold them into UD only at the last step. The paper's reason is exactly that UD has no prefix tags.
• I3. Use the 10-fold cross-validation with the 87.9% figure as the bar for a Mishnaic test of tools/hbo, and first compare a deterministic lexicon-plus-rules tagger with it, before any learned model is added.

For Mova

I1 goes into The lexicon; I2 goes into Pronouns, particles and prepositions (prefix inventory) and 13. Biblical Hebrew in Mova: the tools (the segmenter output); I3 is a measure for 11. Mishnaic Hebrew (hbo-x-mishnaic) and tools/hbo.

Topics: Part-of-speech tagging

Cite

The paper itself, not this card. BibTeX from the library's record of the work. DOI 10.4000/books.aaccademia.3394

@inproceedings{giovannetti2018constructing,
  title = {{Constructing an Annotated Resource for Part-Of-Speech Tagging of Mishnaic Hebrew}},
  author = {Giovannetti, Emiliano and Albanesi, Davide and Bellandi, Andrea and Marchi, Simone and Pecchioli, Alessandra},
  booktitle = {Proceedings of the Fifth Italian Conference on Computational Linguistics (CLiC-it 2018)},
  year = {2018},
  doi = {10.4000/books.aaccademia.3394},
  url = {https://doi.org/10.4000/books.aaccademia.3394}
}

References

18 references, 3 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Meni Adler, Yael Netzer, Yoav Goldberg, David Gabay, and Michael Elhadad. 2008. Tagging a hebrew corpus: the case of participles. In Nicoletta Calzolari (Conference Chair), Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odijk, Stelios Piperidis, and Daniel Tapias, editors, Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08), Marrakech, Morocco, may. European Language Resources Association (ELRA). http://www.lrec-conf.org/proceedings/lrec2008/. ↗ our card
2. Menahem Meni Adler. 2007. Hebrew Morphological Disambiguation: An Unsupervised Stochastic Word-based Approach. PhD Thesis, Ben-Gurion University of the Negev. find
3. Roy Bar-haim, Khalil Sima’an, and Yoad Winter. 2008. Part-of-speech Tagging of Modern Hebrew Text. Nat. Lang. Eng., 14(2):223–251, April. find
4. Andrea Bellandi, Alessia Bellusci, and Emiliano Giovannetti. 2015. Computer Assisted Translation of Ancient Texts: the Babylonian Talmud Case Study. In Natural Language Processing and Cognitive Science, Proceedings 2014, Berlin/Munich. De Gruyter Saur. find
5. Andrea Bellandi, Davide Albanesi, Giulia Benotto, and Emiliano Giovannetti. 2016. Il Sistema Traduco nel Progetto Traduzione del Talmud Babilonese. IJCoL Vol. 2, n. 2, December 2016. Special Issue on ”NLP and Digital Humanities”. Accademia University Press. find
6. Henrik Brink, Joseph Richards, and Mark Fetherolf. 2016. Real-World Machine Learning. Manning Publications Co., Greenwich, CT, USA, 1st edition. find
7. Shay B. Cohen and Noah A. Smith. 2007. Joint Morphological and Syntactic Disambiguation. In Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL). find
8. Miguel Pérez Fernández and John F. Elwolde. 1999. An Introductory Grammar of Rabbinic Hebrew. Interactive Factory, Leiden, The Netherlands. find
9. Péter Halácsy, András Kornai, and Csaba Oravecz. 2007. HunPos: An Open Source Trigram Tagger. In Proceedings of the 45th Annual Meeting of the ACL on Interactive Poster and Demonstration Sessions, ACL ’07, pages 209– 212, Stroudsburg, PA, USA. Association for Computational Linguistics. find
10. Marcus Jastrow. 1971. A dictionary of the Tar-gumim, the Talmud Babli and Yerushalmi, and the Midrashic literature. Judaica Press. find
11. Dror Kamir, Naama Soreq, and Yoni Neeman. 2002. A Comprehensive NLP System for Modern Standard Arabic and Modern Hebrew. In Proceedings of the ACL-02 Workshop on Computational Approaches to Semitic Languages, SEMITIC ’02, pages 1–9, Stroudsburg, PA, USA. Association for Computational Linguistics. find our card
12. Yael Dahan Netzer and Michael Elhadad. 1998. Generating Determiners and Quantifiers in Hebrew. In Proceedings of the Workshop on Computational Approaches to Semitic Languages, Semitic ’98, pages 89–96, Stroudsburg, PA, USA. Association for Computational Linguistics. find our card
13. Yael Netzer, Meni Adler, David Gabay, and Michael Elhadad. 2007. Can You Tag the Modal? You Should. In Proceedings of the 2007 Workshop on Computational Approaches to Semitic Languages: Common Issues and Resources, pages 57–64, Prague, Czech Republic. Association for Computational Linguistics. find
14. Helmut Schmid. 1994. Part-of-speech tagging with neural networks. In Proceedings of the 15th Conference on Computational Linguistics - Volume 1, COLING ’94, pages 172–176, Stroudsburg, PA, USA. Association for Computational Linguistics. find
15. Khalil Sima’an, Alon Itai, Yoad Winter, Alon Altman, and Noa Nativ. 2001. Building a treebank of modern hebrew text. TAL. Traitement automatique des langues, 42(2):347–380. find
16. Fred Skolnik and Michael Berenbaum, editors. 2007. Encyclopaedia Judaica vol. 8. Encyclopaedia Judaica. Macmillan Reference USA, 2 edition. Brovender Chaim and Blau Joshua and Kutscher Eduard Y. and Breuer Yochanan and Eytan Eli sub v. “Hebrew Language”. find
17. Kristina Toutanova, Dan Klein, Christopher D. Manning, and Yoram Singer. 2003. Feature-rich Part-of-speech Tagging with a Cyclic Dependency Network. In Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology - Volume 1, NAACL ’03, pages 173–180, Stroudsburg, PA, USA. Association for Computational Linguistics. find
18. Wido Van Peursen and Constantijn Sikkel. 2014. Hebrew Text Database ETCBC4. type: dataset. find

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/aclbulk-2018-giovannetti-constructing-annotated-resource-part-speech/