Morphological Analysis for the Maltese Language: The challenges of a hybrid system

What it is about

Maltese has two kinds of morphology side by side: a Semitic root-and-pattern (templatic) part, where the root GDB gives the verb gideb ("to lie") with stem variation, and a Romance and English part that is concatenative, where the stem stays whole (eżamina, "to examine"). The authors ask whether one unsupervised technique and one classifier cascade work for both. They reuse the clusters of related words that Borg and Gatt built earlier and have experts rate them. Concatenative clusters are judged better: 61% of them lose no words, against 45% of the templatic ones. Quality ratings correlate strongly with the share of removed words in both groups (0.780 and 0.785). The verb labelling cascade (polarity, indirect object, direct object, tense-aspect-mood, number, gender, person, decision trees in WEKA) scores well on the Ġabra generated test set but worse on 94 verbs from the national corpus, where 76 are templatic and 18 concatenative. Person and TAM do better on concatenative verbs. Large clusters and the segmentation of unseen words are named as the main problems.

Ideas

• I1. Order the cascade by the morphology of the word: decide the clitics and the negative suffix first, then the tense, then person and number, since each decision is easier once the affixes are removed. Test whether a fixed order for Hebrew verbs (prefix and suffix pronouns, then the binyan and tense) beats the reverse order on the same data.
• I2. Report accuracy separately for templatic and concatenative (strong and weak) verbs. In Hebrew, the weak verb classes (pe-nun, lamed-he, ayin-waw) are where stem variation hurts, so a per-class table shows where a rule or a lexicon is needed.
• I3. Use the cluster removal rate as a measure of a generated lexicon: a stem that is too short (their example ittra, "letter", which swept in unrelated words) must be blocked by a minimum stem length rule. Measure how many false groupings the rule removes.

For Mova

I1 is a design choice for the verb chapter The verb, and I3 is a check for the stems in macula dict. I2 is a per-class test for The weak verbs. The paper's own model is not used: Mova keeps the rules and tables explicit.

Cite

The paper itself, not this card. BibTeX from the library's record of the work. DOI 10.18653/v1/w17-1304

@inproceedings{borg2017morphological,
  title = {{Morphological Analysis for the Maltese Language: The challenges of a hybrid system}},
  author = {Borg, Claudia and Gatt, Albert},
  booktitle = {Proceedings of the Third Arabic Natural Language Processing Workshop},
  year = {2017},
  doi = {10.18653/v1/w17-1304},
  url = {https://doi.org/10.18653/v1/w17-1304}
}

References

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

1. Malin Ahlberg, Markus Forsberg, and Mans Hulden. 2014. Semi-supervised learning of morphological paradigms and lexicons. In Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics, Gothenburg, Sweden 26–30 April 2014, pages 569–578. find our card
2. Mathias Creutz and Krista Lagus. 2007. Unsupervised models for morpheme segmentation and morphology learning. ACM Trans. Speech Lang. Process., 4(1):1–34. find
3. Marco Baroni, Johannes Matiasek, and Harald Trost. 2002. Unsupervised discovery of morphologically related words based on orthographic and semantic similarity. In Proceedings of the ACL-02 workshop on Morphological and phonological learning - Volume 6, MPL ’02, pages 48–57. Association for Computational Linguistics. find our card
4. Sajib Dasgupta and Vincent Ng. 2007. High-performance, language-independent morphological segmentation. In NAACL HLT 2007: Proceedings of the Main Conference, pages 155–163. find
5. Anne N. de Roeck and Waleed Al-Fares. 2000. A morphologically sensitive clustering algorithm for identifying Arabic roots. In Proceedings of the 38th Annual Meeting on Association for Computational Linguistics, ACL ’00, pages 199–206. Association for Computational Linguistics. find our card
6. Kenneth R. Beesley. 1996. Arabic finite-state morphological analysis and generation. In Proceedings of the 16th conference on Computational linguistics, pages 89–94. Association for Computational Linguistics. find
7. Vera Demberg. 2007. A language-independent unsupervised model for morphological segmentation. In Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics, pages 920– 927. find
8. Albert Borg and Marie Azzopardi-Alexander. 1997. Maltese: Lingua Descriptive Grammar. Routledge, London and New York. find
9. Claudia Borg and Albert Gatt. 2014. Crowd-sourcing evaluation of automatically acquired, morphologically related word groupings. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14). find
10. Greg Durrett and John DeNero. 2013. Supervised learning of complete morphological paradigms. In Proceedings of the North American Chapter of the Association for Computational Linguistics, pages 1185–1195. find our card
11. Claudia Borg. 2016. Morphology in the Maltese language: A computational perspective. Ph.D. thesis, University of Malta. find
12. Ray Fabri, Michael Gasser, Nizar Habash, George Kiraz, and Shuly Wintner. 2014. Linguistic introduction: The orthography, morphology and syntax of semitic languages. In Natural Language Processing of Semitic Languages, Theory and Applications of Natural Language Processing, pages 3–41. Springer Berlin Heidelberg. find
13. Joseph M. Brincat. 2011. Maltese and other Languages. Midsea Books, Malta. find
14. John J. Camilleri. 2013. A computational grammar and lexicon for Maltese. Master’s thesis, Chalmers University of Technology, Gothenburg, Sweden, September. find
15. Ray Fabri. 2010. Maltese. In Christian Delcourt and Piet van Sterkenburg, editors, The Languages of the New EU Member States, volume 88, pages 791–816. Revue Belge de Philologie et d’Histoire. find
16. Burcu Can and Suresh Manandhar. 2012. Probabilistic hierarchical clustering of morphological paradigms. In Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics, pages 654–663. Association for Computational Linguistics. find
17. Alex Farrugia. 2008. A computational analysis of the Maltese broken plural. Bachelor’s Thesis, University of Malta. find
18. M. L. Forcada, M. Ginestı́-Rosell, J. Nordfalk, J. O’Regan, S. Ortiz-Rojas, J. A. Pérez-Ortiz, F. Sánchez-Martı́nez, G. Ramı́rez-Sánchez, and F. M. Tyers. 2011. Apertium: a free/open-source platform for rule-based machine translation. Machine Translation, 25(2):127–144. find
19. Alexander Clark. 2002. Memory-based learning of morphology with stochastic transducers. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL), pages 513–520. Center for the Study of Language and Information, Stanford (Calif.). find
20. John Goldsmith. 2001. Unsupervised learning of the morphology of a natural language. Computational Linguistics, 27:153–198. find
21. Tamara Schembri. 2006. The Broken Plural in Maltese: An Analysis. Bachelor’s Thesis, University of Malta. find
22. Nizar Habash and Owen Rambow. 2005. Arabic tokenization, part-of-speech tagging and morphological disambiguation in one fell swoop. In Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics, ACL ’05, pages 573– 580, Stroudsburg, PA, USA. Association for Computational Linguistics. find our card
23. Patrick Schone and Daniel Jurafsky. 2000. Knowledge-free induction of morphology using latent semantic analysis. In Proceedings of the 2nd workshop on Learning language in logic and the 4th conference on Computational natural language learning - Volume 7, ConLL ’00, pages 67–72. Association for Computational Linguistics. find
24. Nizar Habash, Owen Rambow, and George Kiraz. 2005. MAGEAD: A Morphological Analyzer and Generator for the Arabic Dialects. In Proceedings of the ACL Workshop on Computational Approaches to Semitic Languages, pages 17–24. The Association for Computer Linguistics. find our card
25. Patrick Schone and Daniel Jurafsky. 2001. Knowledge-free induction of inflectional morphologies. In Proceedings of the second meeting of the North American Chapter of the Association for Computational Linguistics on Language technologies, NAACL ’01, pages 1–9. Association for Computational Linguistics. find our card
26. Mark Hall, Eibe Frank, Geoffrey Holmes, Bernhard Pfahringer, Peter Reutemann, and Ian H. Witten. 2009. The weka data mining software: an update. SIGKDD Explor. Newsl., 11(1):10–18. find
27. Kairit Sirts and Sharon Goldwater. 2013. Minimally-supervised morphological segmentation using adaptor grammars. Transactions of the Association for Computational Linguistics, 1:255–266. find
28. Harald Hammarström and Lars Borin. 2011. Unsupervised learning of morphology. Computational Linguistics, 37:309–350. find
29. Samarth Keshava and Emily Pitler. 2006. A simpler, intuitive approach to morpheme induction. In PAS-CAL Challenge Workshop on Unsupervised Segmentation of Words into Morphemes, pages 31–35. find
30. Benjamin Snyder and Regina Barzilay. 2008. Unsupervised multilingual learning for morphological segmentation. In Proceedings of ACL-08: HLT, pages 737–745, Columbus, Ohio. Association for Computational Linguistics. find
31. Oskar Kohonen, Sami Virpioja, and Krista Lagus. 2010. Semi-supervised learning of concatenative morphology. In Proceedings of the 11th Meeting of the ACL Special Interest Group on Computational Morphology and Phonology, SIGMORPHON ’10, pages 78–86, Stroudsburg, PA, USA. Association for Computational Linguistics. find
32. Michael Spagnol. 2011. A tale of two morphologies. Verb structure and argument alternations in Maltese. Ph.D. thesis, University of Konstanz. find
33. Antal Van den Bosch and Walter Daelemans. 1999. Memory-based morphological analysis. In Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics, pages 285–292. find
34. Mikko Kurimo, Sami Virpioja, Ville Turunen, and Krista Lagus. 2010. Morpho Challenge competition 2005–2010: evaluations and results. In Proceedings of the 11th Meeting of the ACL Special Interest Group on Computational Morphology and Phonology, SIGMORPHON ’10, pages 87–95. Association for Computational Linguistics. find
35. David Yarowsky and Richard Wicentowski. 2000. Minimally supervised morphological analysis by multimodal alignment. In Proceedings of the 38th Annual Meeting on Association for Computational Linguistics, ACL ’00, pages 207–216, Stroudsburg, PA, USA. Association for Computational Linguistics. find
36. Karthik Narasimhan, Regina Barzilay, and Tommi S. Jaakkola. 2015. An unsupervised method for uncovering morphological chains. Transactions of the Association for Computational Linguistics (TACL), 3:157–167. find
37. Hoifung Poon, Colin Cherry, and Kristina Toutanova. 2009. Unsupervised morphological segmentation with log-linear models. In Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, NAACL ’09, pages 209–217. find
38. Aarne Ranta. 2011. Grammatical framework: programming with multilingual grammars. CSLI studies in computational linguistics. CSLI Publications, find

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/aclbulk-2017-borg-morphological-analysis-maltese-language-challenges/