Handling Stress in Finite-State Morphological Analyzers for Ancient Greek and Ancient Hebrew

What it is about

The authors argue that finite-state analysers can model lexical stress if the lexicon carries control characters beyond the surface form. They build two Apertium-based prototypes with the lexd compiler and two-level rules: Ancient Greek, with full accent placement, and Ancient Hebrew, with stress movement for the vav-consecutive forms, which move the stress to the penultimate syllable. Analysis coverage is 95.2% of tokens in the Greek New Testament (146,265 of 153,665) and 64.2% of tokens in Hebrew Genesis (13,201 of 20,573). Both analysers overgenerate: about 8% of Greek words, and in Hebrew some pronominal forms. Nominal morphology in the Hebrew analyser is incomplete.

Ideas

• I1. Describe the Hebrew verb system with interlaced lexical entries (a root, with slots for each stem pattern) instead of listing forms; the same root table can serve the weak verbs in The weak verbs.
• I2. Carry stress as a feature on the verb: a vav-consecutive form gets a stress-moved flag that derives the penultimate vowel and the deleted final syllable. Mova derives these forms rather than storing them.
• I3. Use the paper's per-book coverage (Genesis 64.2%) as the first yardstick for the tools/hbo lexicon: report coverage per book, and treat any drop as a regression.
• I4. Test the overgeneration rate on a held-out book with a fixed list of known-wrong forms, the same way they report it.

For Mova

I1 and I2 apply to The verb and 07-weak-verbs.md; I3 is a measure for tools/hbo and macula; I4 is a test for the same. The paper is licensed non-commercial, so we use only the summary and do not carry its code or tables into a release.

Cite

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

@inproceedings{swanson2022handling,
  title = {{Handling Stress in Finite-State Morphological Analyzers for Ancient Greek and Ancient Hebrew}},
  author = {Swanson, Daniel G. and Tyers, Francis M.},
  booktitle = {Proceedings of the Second Workshop on Language Technologies for Historical and Ancient Languages},
  year = {2022},
  url = {https://aclanthology.org/2022.lt4hala-1.15/}
}

References

13 references, 1 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Crane, G. (1991). Generating and Parsing Classical Greek. Literary and Linguistic Computing, 6(4):243–245, 01. find
2. Forcada, M. L., Ginestı́-Rosell, M., Nordfalk, J., O’Regan, J., Ortiz-Rojas, S., Pérez-Ortiz, J. A., Sánchez-Martı́nez, F., Ramı́rez-Sánchez, G., and Tyers, F. M. (2011). Apertium: a free/open-source platform for rule-based machine translation. Machine translation, 25(2):127–144. find
3. Gesenius, W. and Kautzsch, E. (2006). Gesenius’ Hebrew Grammar. Dover Publications. find
4. Karttunen, L. (1991). Finite-state constraints. In Proceedings of the International Conference on Current Issues in Computational Linguistics. find
5. Khanna, T., Washington, J., Tyers, F., Bayatlı, S., Swanson, D., Pirinen, T., Tang, I., and Alòs i Font, H. (2021). Recent advances in apertium, a free / open-source rule-based machine translation platform for low-resource languages. Machine Translation. find
6. Koskenniemi, K. (1983). Two-level Morphology: A General Computational Model for Word-Form Recognition and Production. phdthesis. find
7. Lindén, K., Silfverberg, M., and Pirinen, T. (2009). Hfst tools for morphology–an efficient open-source package for construction of morphological analyzers. In International Workshop on Systems and Frameworks for Computational Morphology, pages 28–47. Springer. find
8. Packard, D. W. (1973). Computer-assisted morphological analysis of Ancient Greek. In COLING 1973 Volume 2: Computational And Mathematical Linguistics: Proceedings of the International Conference on Computational Linguistics. find
9. Smith, N. (2016). Morphological analysis of historical languages. Bulletin of the Institute of Classical Studies, 59(2):89–102. find
10. Swanson, D. and Howell, N. (2021). Lexd: A finite-state lexicon compiler for non-suffixational morphologies. In Mika Hämäläinen, et al., editors, Multilingual Facilitation. University of Helsinki Library. find
11. van Emde Boas, E., Rijksbaron, A., Huitink, L., and de Bakker, M. (2019). The Cambridge Grammar of Classical Greek. Cambridge University Press. find
12. Wintner, S. (2008). Strengths and weaknesses of finite-state technology: a case study in morphological grammar development. 14(4):457–469. find
13. Yona, S. and Wintner, S. (2008). A finite-state morphological grammar of hebrew. 14(2):173–190. find our card

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/aclbulk-2022-swanson-handling-stress-finite-state-morphological/