Article in:Studies in Language: Online-First Articles
Derivation predicting inflection
A quantitative study of the relation between derivational history and inflectional behavior in Latin
In this paper, we investigate the value of derivational information in predicting the inflectional behavior of lexemes. We focus on Latin, for which large-scale data on both inflection and derivation are easily available. We train boosting tree classifiers to predict the inflection class of verbs and nouns with and without different pieces of derivational information. For verbs, we also model inflectional behavior in a word-based fashion, training the same type of classifier to predict wordforms given knowledge of other wordforms of the same lexemes. We find that derivational information is indeed helpful, and document an asymmetry between the beginning and the end of words, in that the final element in a word is highly predictive, while prefixes prove to be uninformative. The results obtained with the word-based methodology also allow for a finer-grained description of the behavior of different pairs of cells.
- 2.Data collection and annotation
- 3.Predicting inflection classes
- 3.2Predicting the conjugation of verbs
- 3.3Predicting the declension of nouns
- 4.A word-based alternative: Predicting verb forms
- 4.2The information-theoretic approach to the PCFP
- 4.3The PCFP as a classification problem
Published online: 21 January 2022
Ackerman, Farrell, James P. Blevins & Robert Malouf
Ackerman, Farrell & Robert Malouf
Albright, Adam C. & Bruce P. Hayes
2018 Classifications flexionnelles. Étude quantitative des structures de paradigmes. Paris: Université Sorbonne Paris Cité-Université Paris Diderot PhD dissertation.
Beniamine, Sacha, Olivier Bonami & Benoît Sagot
Bonami, Olivier & S. Beniamine
Bonami, Olivier & Gilles Boyé
2006 Deriving inflectional irregularity. In Stefan Müller (ed.), Proceedings of the 13th International Conference on Head Driven Phrase Structure Grammar, Varna, 361–380. Stanford, CA: CSLI Publications. http://cslipublications.stanford.edu/HPSG/2006/bonami-boye.pdf
Boyé, Gilles & Gauvain Schalchli
Brown, Dunstan, Marina Chumakina & Greville G. Corbett
Brown, Dunstan & Andrew Hippisley
Budassi, Marco & Eleonora Litta
Corbett, Greville G.
Delatte, Louis, Étienne Evrard, Suzanne Govaerts & Joseph Denooz
Dressler, Wolfgang U.
Friedman, Jerome H.
Guzmán Naranjo, Matías
Guzmán Naranjo, Matías & Olivier Bonami
Litta, Eleonora & Marco Passarotti
Mason, Llew, Jonathan Baxter, Peter L. Bartlett & Marcus R. Frean
McGillivray, Barbara & Adam Kilgarriff
Passarotti, Marco, Marco Budassi, Eleonora Litta & Paolo Ruffolo
Pedregosa, Fabian, Gaël Varoquaux, Alexandre Gramfort, Vincent Michel, Bertrand Thirion, Olivier Grisel, Mathieu Blondel, Peter Prettenhofer, Ron Weiss, Vincent Dubourg, Jake Vanderplas, Alexandre Passos, David Cournapeau, Matthieu Brucher, Matthieu Perrot & Édouard Duchesnay
2020 Predictability in Latin inflection. An entropy-based approach. Bergamo/Pavia: Università di Bergamo-Università di Pavia PhD dissertation.
Pellegrini, Matteo & Marco Passarotti
Plaster, Keith, Maria Polinsky & Boris Harizanov
Stump, Gregory T.