Supervised Learning of Complete Morphological Paradigms

What it is about

The paper predicts every inflected form of a lemma from its base form. First it aligns base forms with inflected forms to build an inventory of orthographic transformation rules, prefix, suffix and stem changes. Then a semi-Markov conditional random field learns where each rule applies, and it predicts all forms of one lemma jointly, so that one consistent analysis is used. The training data are Wiktionary inflection tables. Averaged over three languages and two parts of speech, complete paradigms are predicted with 86.1% accuracy and single forms with 94.9%. Per-form accuracy on held-out base forms runs from 88.9% (German nouns) to 99.7% (Spanish verbs). Joint prediction cuts the error on exact table matches by 35% relative to the factored model.

Ideas

• I1. en/src/morph.rs: build a rule inventory for English by aligning each lemma with its inflected forms in data/forms.tsv, and count how many rules cover the table. Measure the rule coverage on EWT test forms, and report the rules that fail.
• I2. Joint consistency filter: for one lemma, accept only inflected forms that share a single stem rule, and reject the rest. Measure the exact-table match on held-out English lemmas with and without the filter, using a two-fold split and the negative control of a random filter.
• I3. Error breakdown by rule, as in the paper's Table 6: group the English errors of en morph-eval by rule family (for example -ies, doubled final consonant, silent e). This shows which rule to repair first, and the count per family is the measure.

For Mova

The code is en/src/morph.rs and en/src/lexgen.rs, with en morph-eval for the checks. The chapters are 13. Verbs for the verb rules and 06. Spelling rules: inflection, derivation, compounds and national standards for the orthographic changes. The paper has no English data (German, Spanish, Finnish), and its tables are Wiktionary-derived, so use it for method ideas and tests only, never in what is built. Measure first: exact-table match for English lemmas, two runs identical.

Cite

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

@inproceedings{durrett2013supervised,
  title = {{Supervised Learning of Complete Morphological Paradigms}},
  author = {Durrett, Greg and DeNero, John},
  booktitle = {NAACL-HLT 2013 (Atlanta)},
  year = {2013},
  url = {https://aclanthology.org/N13-1138/}
}

References

32 references, 2 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. R. H. Baayen, R. Piepenbrock, and L. Gulikers. 1995. The CELEX Lexical Database (Release 2). Linguistic Data Consortium, University of Pennsylvania. find
2. Alexander Clark. 2001. Partially Supervised Learning of Morphology with Stochastic Transducers. In Proceedings of Natural Language Processing Pacific Rim Symposium, pages 341–348, Tokyo, Japan. find
3. Mathias Creutz and Krista Lagus. 2007. Unsupervised Models for Morpheme Segmentation and Morphology Learning. ACM Transactions on Speech and Language Processing, 4(1):3:1–3:34, Feb. find
4. Sajib Dasgupta and Vincent Ng. 2007. High Performance, Language-Independent Morphological Segmentation. In Proceedings of the North American Chapter of the Association for Computational Linguistics. find
5. Grégoire Détrez and Aarne Ranta. 2012. Smart Paradigms and the Predictability and Complexity of Inflectional Morphology. In Proceedings of the European Chapter of the Association for Computational Linguistics. find
6. Liviu P. Dinu, Vlad Niculae, and Octavia-Maria Şulea. 2012. Learning How to Conjugate the Romanian Verb: Rules for Regular and Partially Irregular Verbs. In Proceedings of the European Chapter of the Association for Computational Linguistics. find
7. Markus Dreyer and Jason Eisner. 2011. Discovering Morphological Paradigms from Plain Text Using a Dirichlet Process Mixture Model. In Proceedings of Empirical Methods in Natural Language Processing, pages 616–627, Edinburgh, Scotland, UK. find
8. Jason Eisner. 2002. Parameter Estimation for Probabilistic Finite-State Transducers. In Proceedings of the Association for Computational Linguistics. find
9. Markus Forsberg, Harald Hammarström, and Aarne Ranta. 2006. Morphological Lexicon Extraction from Raw Text Data. In Proceedings of Advances in Natural Language Processing. find
10. John Goldsmith. 2001. Unsupervised Learning of the Morphology of a Natural Language. Computational Linguistics, 27(2):153–198, June. find
11. Sharon Goldwater, Thomas L. Griffiths, and Mark Johnson. 2009. A Bayesian Framework for Word Segmentation: Exploring the Effects of Context. Cognition, 112(1):21–54. find
12. Sittichai Jiampojamarn, Colin Cherry, and Grzegorz Kondrak. 2008. Joint Processing and Discriminative Training for Letter-to-Phoneme Conversion. In Proceedings of the Association for Computational Linguistics. find
13. Teuvo Kohonen. 1986. Dynamically Expanding Context, With Application to the Correction of Symbol Strings in the Recognition of Continuous Speech. In Proceedings of the International Conference on Pattern Recognition. find
14. Shen Li, João V. Graça, and Ben Taskar. 2012. Wiki-ly Supervised Part-of-speech Tagging. In Proceedings of Empirical Methods in Natural Language Processing. find
15. Krister Lindén and Jussi Tuovila. 2009. Corpus-based Paradigm Selection for Morphological Entries. In Proceedings of the Nordic Conference of Computational Linguistics. find
16. Krister Lindén. 2008. A Probabilistic Model for Guessing Base Forms of New Words by Analogy. In Proceedings of Computational Linguistics and Intelligent Text Processing. find
17. Dong C. Liu and Jorge Nocedal. 1989. On the limited memory BFGS method for large scale optimization. Mathematical Programming, 45(3):503–528, December. find
18. Christian Monson. 2008. ParaMor: From Paradigm Structure to Natural Language Morphology Induction. Ph.D. thesis, Carnegie Mellon University. find
19. Jason Naradowsky and Sharon Goldwater. 2009. Improving Morphology Induction by Learning Spelling Rules. In Proceedings of the International Joint Conferences on Artificial Intelligence. find
20. Jose Oncina and Marc Sebban. 2006. Learning Stochastic Edit Distance: Application in Handwritten Character Recognition. Pattern Recognition, 39(9):1575– 1587, September. find
21. Hoifung Poon, Colin Cherry, and Kristina Toutanova. 2009. Unsupervised Morphological Segmentation with Log-Linear Models. In Proceedings of the North American Chapter of the Association for Computational Linguistics. find
22. Aarne Ranta. 2011. Grammatical Framework: Programming with Multilingual Grammars. CSLI Publications, Stanford. find
23. Sunita Sarawagi and William W. Cohen. 2004. Semi-Markov Conditional Random Fields for Information Extraction. In Advances in Neural Information Processing Systems 17. find
24. Patrick Schone and Daniel Jurafsky. 2001. Knowledge-Free Induction of Inflectional Morphologies. In Proceedings of the North American Chapter of the Association for Computational Linguistics. find our card
25. Ksenia Shalonova and Bruno Golénia. 2010. Weakly Supervised Morphology Learning for Agglutinating Languages Using Small Training Sets. In Proceedings of the Conference on Computational Linguistics. find
26. Benjamin Snyder and Regina Barzilay. 2008. Unsupervised Multilingual Learning for Morphological Segmentation. In Proceedings of the Association for Computational Linguistics. find
27. Kari Torkkola. 1993. An Efficient Way to Learn English Grapheme-to-Phoneme Rules Automatically. In Proceedings of the International Conference on Acoustics, Speech, and Signal Processing: Speech Processing - Volume II. find
28. Kristina Toutanova and Colin Cherry. 2009. A Global Model for Joint Lemmatization and Part-of-Speech Prediction. In Proceedings of the Association for Computational Linguistics. find our card
29. Richard Wicentowski. 2004. Multilingual Noise-Robust Supervised Morphological Analysis Using the Word-Frame Model. In Proceedings of the ACL Special Interest Group in Computational Phonology. find
30. David Yarowsky and Richard Wicentowski. 2000. Minimally Supervised Morphological Analysis by Multimodal Alignment. In Proceedings of the Association for Computational Linguistics. find
31. Rémi Zajac. 2001. Morpholog: Constrained and Supervised Learning of Morphology. In Proceedings of the Conference on Natural Language Learning. find
32. Torsten Zesch, Christof Müller, and Iryna Gurevych. 2008. Extracting Lexical Semantic Knowledge from Wikipedia and Wiktionary. In Proceedings of Language Resources and Evaluation. find

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/lex-2013-durrett-morphological-paradigms/