Word Segmentation for Akkadian Cuneiform

What it is about

The authors segment Akkadian cuneiform lines into words, treating the logosyllabic script as close to Chinese and Japanese. They compare three families of methods: rule-based (bigram, prefix/suffix, Tango), dictionary-based (MaxMatch and variants, minimum word count, maximum probability) and statistical or machine-learning classifiers (C4.5, MaxEnt, Naive Bayes, kNN, SVM, CRF, HMM, plus a meta-classifier). The data are Middle Babylonian tablets split 80:20 per tablet; Old Babylonian and Neo-Assyrian serve as further stages. The average-word-length baseline reaches a boundary F of about 43 and a word F of about 21. Dictionary methods are best (MinWCMatch: boundary F about 73, word F about 60), while most learners barely beat the baseline. Only Tango among the rule methods beats it.

Ideas

• I1. Score the tools/hbo segmenter with the same triad: boundary F, word F and a window-based score (WindowDiff). Split the MACULA data per verse or per book, not per line, so no neighbouring line leaks into the test part, as the authors did per tablet.
• I2. A maximum-match segmenter over the lex and pre tables as a second deterministic baseline for unpointed text. The paper's finding that dictionary matching beats learners on a small corpus argues for the tables before any learned step.
• I3. Keep an average-length style floor in every report (here: one word per fixed number of letters), so a new mode of tools/hbo is always compared with something trivial.

For Mova

I1–I3 go into tools/hbo, as its evaluation and its baselines for the unpointed mode. Akkadian is not a Mova language yet, so nothing goes into languages/.

Topics: Akkadian and cuneiform NLP

Cite

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

@inproceedings{homburg2016word,
  title = {{Word Segmentation for Akkadian Cuneiform}},
  author = {Homburg, Timo and Chiarcos, Christian},
  booktitle = {Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)},
  year = {2016},
  url = {https://aclanthology.org/L16-1642/}
}

References

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

1. Ando, R. K. and Lee, L. (2000). Mostly-unsupervised statistical segmentation of japanese: Applications to kanji. In Proceedings of the 1st North American Chapter of the Association for Computational Linguistics Conference, NAACL 2000, pages 241–248, Stroudsburg, PA, USA. Association for Computational Linguistics. find
2. Barthlemy, F. (1998). A morphological analyzer for Akkadian verbal forms with a model of phonetic transformations. In Proceedings of the ACL-1998 Workshop on Computational Approaches to Semitic Languages, Montral. find our card
3. Barthlemy, F. (2009). The Karamel System and Semitic languages: Structured multi-tiered morphology. In Proceedings of the EACL 2009 Workshop on Computational Approaches to Semitic Languages, page 1018, Athens, Greece. find our card
4. Borger, R. (2004). Mesopotamisches Zeichenlexikon. Ugarit-Verlag. find
5. Chen, K.-J. and Liu, S.-H. (1992). Word identification for mandarin chinese sentences. In Proceedings of the 14th Conference on Computational Linguistics - Volume 1, COLING ’92, pages 101–107, Stroudsburg, PA, USA. Association for Computational Linguistics. find
6. Cohen, J. D., Duncan, D., Snyder, D., Cooper, J., Kumar, S., Hahn, D., Chen, Y., Purnomo, B., and Graet-tinger, J. (2004). iClay: Digitizing Cuneiform. In Proceedings of the 5th International Conference on Virtual Reality, Archaeology and Intelligent Cultural Heritage (VAST-2004), pages 135–143, Aire-la-Ville, Switzerland, Switzerland. Eurographics Association. Collins, T., Woolley, S., Gehlken, E., Lewis, A., Munoz, L. H., and Ch’ng, E. (accepted). Automated reconstruction of virtual fragmented cuneiform tablets. Electronics Letters (IET). find
7. Gelb, I. (1957). Glossary of Old Akkadian. University of Chicago Press, Chicago, Illinois. find
8. Ikeda, J. (2007). Early Japanese and early Akkadian writing systems. a contrastive survey of Kunogenesis. In Proceedings of Origins of Early Writing Systems, Peking University, Beijing. find
9. Islam, M. A., Inkpen, D., and Kiringa, I. (2007). A generalized approach to word segmentation using maximum length descending frequency and entropy rate. In Computational Linguistics and Intelligent Text Processing, pages 175–185. Springer. find
10. Jaworski, W. (2008). Contents modelling of neo-sumerian ur III economic text corpus. In Proceedings of the 22nd International Conference on Computational Linguistics (Coling 2008), pages 369–376, Manchester, UK, August. Coling 2008 Organizing Committee. find
11. Kataja, L. and Koskenniemi, K. (1988). Finite-state description of Semitic morphology: A case study of Ancient Akkadian. In Proceedings of COLING 1988. find
12. Khait, I. (accepted). Cuneiform Labs: Annotating Akkadian corpora. In Rencontre Assyriologique Internationale (RAI-2015), Geneva and Bern, Switzerland, June 22-26, 2015. find
14. Low, J. K., Ng, H. T., and Guo, W. (2005). A maximum entropy approach to chinese word segmentation. In Proceedings of the Fourth SIGHAN Workshop on Chinese Language Processing, volume 1612164. find
15. Macks, A. (2002). Parsing Akkadian Verbs with Prolog. In Proceedings of the ACL-02 Workshop on Computational Approaches to Semitic Languages, Philadelphia, Pennsylvania. find our card
16. Mara, H., Krmker, S., Jakob, S., and Breuckmann, B. (2010). GigaMesh and Gilgamesh 3D Multiscale Integral Invariant Cuneiform Character Extraction. In Alessandro Artusi, et al., editors, VAST: International Symposium on Virtual Reality, Archaeology and Intelligent Cultural Heritage. The Eurographics Association. find
17. Palmer, D. and Burger, J. (1997). Chinese word segmentation and information retrieval. In AAAI Spring Symposium on Cross-Language Text and Speech Retrieval, pages 175–178. find
18. Papageorgiou, C. P. (1994). Japanese word segmentation by hidden markov model. In Proceedings of the workshop on Human Language Technology, pages 283–288. Association for Computational Linguistics. find
19. Pengyu, L., Jingchuan, P., Du Mingming, L. X., and Lijun, J. (2014). A lexicon-corpus-based unsupervised chinese word segmentation approach. International Journal On Smart Sensing And Intelligent Systems, 7(1). find
20. Pevzner, L. and Hearst, M. A. (2002). A critique and improvement of an evaluation metric for text segmentation. Computational Linguistics, 28(1):19–36. find
21. Raman, A. (2006). A dictionary-augmented maximum entropy tagging approach to chinese word segmentation. find
22. Scaiano, M. and Inkpen, D. (2012). Getting more from segmentation evaluation. In Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 362–366. Association for Computational Linguistics. find
23. Snyder, B., Barzilay, R., and Knight, K. (2010). A statistical model for lost language decipherment. In Proceedings of ACL-2010, Upsala, Sweden. find
24. Song, D. and Sarkar, A. (2008). Training a perceptron with global and local features for chinese word segmentation. In IJCNLP, pages 143–146. Citeseer. find
25. Sproat, R. and Emerson, T. (2003). The first international chinese word segmentation bakeoff. In Proceedings of the second SIGHAN workshop on Chinese language processing-Volume 17, pages 133–143. Association for Computational Linguistics. find
26. Subodh, K., Snyder, D., Duncan, D., Cohen, J., and Cooper, J. (2003). Digital preservation of ancient cuneiform tablets using 3D-scanning. In Proceedings of the 4th International Conference on 3-D Digital Imaging and Modeling (3DIM-2003), pages 326–333. IEEE. find
27. Tinney, S. et al. (2006). The Pennsylvania Sumerian dictionary. http://psd.museum.upenn.edu/epsd1/. ↗
28. Tyndall, S. (2012). Toward automatically assembling Hittite-language cuneiform tablet fragments into larger texts. In Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics, pages 243– 247. Association for Computational Linguistics. find
29. Valentin Tablan Wim Peters, Diana Maynard, H. C. (2006). Creating tools for morphological analysis of Sumerian. In Proceedings of the 5th International Conference on Language Resources and Evaluation (LREC-2006), pages 1762–1765, Genova, Italy. find

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/lingbulk-2016-homburg-word-segmentation-akkadian-cuneiform/