A Probabilistic Morphological Analyzer for Syriac

What it is about

The authors build a data-driven morphological analyzer for Syriac, an unvocalized Aramaic dialect with no existing tools, which needs only labelled data. Their training set is the Peshitta New Testament in Kiraz's 1994 annotation (109,640 tokens). The analyzer is a pipeline of maximum-entropy Markov models: segmentation into prefix, stem and suffix; baseform linkage; root linkage; suffix tagging; and stem tagging, with n-best beams passed between stages. Unknown words back off to a consonant-level BI model and to edit-script "lemma classes" borrowed from Morfette. Under ten-fold cross-validation the joint model reaches 86.47% word accuracy against an 80.76% naive baseline (a 29.7% error reduction), and about 80% with roughly 34,500 training tokens.

Ideas

• I1. Consonant-level segmentation for unknown words: label each consonant as beginning or inside a prefix, stem or suffix, and forbid any transition that puts a prefix after a stem. For tools/hbo, use this as the fallback when the lex or pre tables have no entry for an unpointed token; the legal-transition rule is a finite-state constraint and stays deterministic.
• I2. Lemma classes for unknown lemmas: encode a lemma as the list of insert and delete operations (with positions) that turn the stem into it, and count which operations recur. In The lexicon of Biblical Aramaic this gives a rule-based guess for an unseen Aramaic lemma, checkable against the dictionary.
• I3. Report decision-level accuracy (the number of decisions a human annotator would correct) next to word accuracy, and keep the naive most-frequent baselines as the floor in the same table. The baseline for an unknown root is the first three consonants of the baseform; that is a cheap rule to test in The lexicon of Biblical Aramaic.

For Mova

I1 goes into tools/hbo (segmenter fallback for unknown tokens) and is recorded in 13. Biblical Hebrew in Mova: the tools. I2 goes into The lexicon of Biblical Aramaic. I3 is a measurement for tools/hbo and for the evaluation notes in Aramaic in Mova: what it would need. The paper's joint pipeline is a design sketch only; nothing of it is a neural model that Mova would run at test time.

Cite

The paper itself, not this card. BibTeX from the library's record of the work.

@inproceedings{mcclanahan2010probabilistic,
  title = {{A Probabilistic Morphological Analyzer for Syriac}},
  author = {McClanahan, Peter and Busby, George and Haertel, Robbie and Heal, Kristian and Lonsdale, Deryle and Seppi, Kevin and Ringger, Eric},
  booktitle = {Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing},
  year = {2010},
  url = {https://aclanthology.org/D10-1079/}
}

References

21 references, 7 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Roy Bar-haim, Khalil Sima’an, and Yoad Winter. 2008. Part-of-speech tagging of modern hebrew text. Natural Language Engineering, 14(2):223–251. ↗
2. British and Foreign Bible Society, editors. 1920. The New Testament in Syriac. Oxford: Frederick Hall. find
3. Grzegorz Chrupała, Georgiana Dinu, and Josef van Genabith. 2008. Learning morphology with Morfette. In Proceedings of the Sixth International Language Resources and Evaluation (LREC’08). ↗ our card
4. Grzegorz Chrupała. 2006. Simple data-driven context-sensitive lemmatization. In Procesamiento del Lenguaje Natural, volume 37, pages 121 – 127. Ezra Daya, Dan Roth, and Shuly Wintner. Identifying Semitic roots: Machine learning with linguistic constraints. Computational Linguistics, 34(3):429–448. find our card
5. Mona Diab, Kadri Hacioglu, and Daniel Jurafsky. 2004. Automatic tagging of Arabic text: From raw text to base phrase chunks. In Proceedings of the 5th Meeting of the North American Chapter of the Association for Computational Linguistics/Human Language Technologies Conference (HLT-NAACL04), pages 149–152. ↗
6. Jenny Rose Finkel, Christopher D. Manning, and Andrew Y. Ng. 2006. Solving the problem of cascading errors: Approximate Bayesian inference for linguistic annotation pipelines. In EMNLP ’06: Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing, pages 618–626. Association for Computational Linguistics. ↗
7. Nizar Habash and Owen Rambow. 2005. Arabic tokenization, part-of-speech tagging and morphological disambiguation in one fell swoop. In ACL ’05: Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics, pages 573–580. Association for Computational Linguistics. ↗ our card
8. Nizar Habash and Owen Rambow. 2007. Arabic diacritization through full morphological tagging. In Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Companion Volume, Short Papers, pages 53–56. Association for Computational Linguistics. ↗ our card
9. Robbie Haertel, Peter McClanahan, and Eric K. Ringger. 2010. Automatic diacritization for low-resource languages using a hybrid word and consonant cmm. In Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, pages 519–527. Association for Computational Linguistics. find
10. Jan Hajič and Barbora Hladká. 1998. Tagging inflective languages: Prediction of morphological categories for a rich, structured tagset. In Proceedings of the 17th International Conference on Computational Linguistics, pages 483–490. Association for Computational Linguistics. ↗
11. George Kiraz. 1994. Automatic concordance generation of Syriac texts. In R. Lavenant, editor, VI Symposium Syriacum 1992, pages 461–. find
12. George Anton Kiraz. 2000. Multitiered nonlinear morphology using multitape finite automata: a case study on Syriac and Arabic. Computational Linguistics, 26:77–105. ↗ our card
13. Taku Kudo, Kaoru Yamamoto, and Yuji Matsumoto. 2004. Applying conditional random fields to japanese morphological analysis. In Proceedings of EMNLP, 2008. pages 230–237. find
14. Young-Suk Lee, Kishore Papineni, Salim Roukos, Ossama Emam, and Hany Hassan. 2003. Language model based Arabic word segmentation. In ACL ’03: Proceedings of the 41st Annual Meeting on Association for Computational Linguistics, pages 399–406. Association for Computational Linguistics. ↗
15. Saib Mansour, Khalil Sima’an, and Yoad Winter. 2007. Smoothing a lexicon-based pos tagger for Arabic and Hebrew. In Semitic ’07: Proceedings of the 2007 Workshop on Computational Approaches to Semitic Languages, pages 97–103. Association for Computational Linguistics. ↗ our card
16. Emad Mohamed and Sandra Kübler. 2010a. Arabic part of speech tagging. In Proceedings of the Seventh International Language Resources and Evaluation (LREC’10). ↗
17. Emad Mohamed and Sandra Kübler. 2010b. Is Arabic part of speech tagging feasible without word segmentation? In Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, pages 705–708. Association for Computational Linguistics. find
18. Vladimír Petkevič. 2001. Grammatical agreement and automatic morphological disambiguation of inflectional languages. In TSD ’01: Proceedings of the 4th International Conference on Text, Speech and Dialogue, pages 47–53. Springer-Verlag. ↗
19. Danny Shacham and Shuly Wintner. 2007. Morphological disambiguation of Hebrew: a case study in classifier combination. In Proceedings of EMNLP-CoNLL 2007, the Conference on Empirical Methods in Natural Language Processing and the Conference on Computational Natural Language Learning. Association for Computational Linguistics. find our card
20. Noah A. Smith, David A. Smith, and Roy W. Tromble. 2005. Context-based morphological disambiguation with random fields. In HLT ’05: Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing, pages 475–482. Association for Computational Linguistics. ↗
21. K. Toutanova and C. Manning. 2000. Enriching the knowledge sources used in a maximum entropy part-of-speech tagger. In Proceedings of EMNLP, pages 63–70. ↗

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/aclbulk-2010-mcclanahan-probabilistic-morphological-analyzer-syriac/