Adaptor Grammars for Learning Non-Concatenative Morphology

Joint Bayesian Morphology learning for Dravidian languages

In this paper a methodology for learning the complex agglutinative morphology of some Indian languages using Adaptor Grammars and morphology rules is presented. Adaptor grammars are a compositional Bayesian framework for grammatical inference, where we define a morphological grammar for agglutinative languages and morphological boundaries are inferred from a plain text corpus. Once morphologica...

Learning non-concatenative morphology

Recent work in computational psycholinguistics shows that morpheme lexica can be acquired in an unsupervised manner from a corpus of words by selecting the lexicon that best balances productivity and reuse (e.g. Goldwater et al. (2009) and others). In this paper, we extend such work to the problem of acquiring non-concatenative morphology, proposing a simple model of morphology that can handle ...

The application of two-level morphology to non-concatenative German morphology

In this paper2 I describe a hybrid system for morphological analysis and synthesis. This system consists of two parts. The treatment of morphonology and non-concatenative morphology is based on the two-level approach proposed by Koskenniemi (1983). For the concatenative part of morphosyntax (i.e. affixation) a grammar based on featureunification is made use of. Both parts rely on a morph lexico...

Unsupervised learning of Arabic non-concatenative morphology

Evaluating Sequence Alignment for Learning Inflectional Morphology

This work examines CRF-based sequence alignment models for learning natural language morphology. Although these systems have performed well for a limited number of languages, this work, as part of the SIGMORPHON 2016 shared task, specifically sets out to determine whether these models handle non-concatenative morphology as well as previous work might suggest. Results, however, indicate a strong...