Using morphology and syntax together in unsupervised learning

Authors:
Yu Hu;Irina Matveeva;John Goldsmith;Colin Sprague
Affiliations:
The University of Chicago, Chicago, IL;The University of Chicago, Chicago, IL;The University of Chicago, Chicago, IL;The University of Chicago, Chicago, IL
Venue:
PMHLA '05 Proceedings of the Workshop on Psychocomputational Models of Human Language Acquisition
Year:
2005

Citing 4
Cited 5

Class-based n-gram models of natural language

Computational Linguistics
Stochastic Complexity in Statistical Inquiry Theory

Stochastic Complexity in Statistical Inquiry Theory
Modeling and learning multilingual inflectional morphology in a minimally supervised framework

Modeling and learning multilingual inflectional morphology in a minimally supervised framework
Unsupervised learning of the morphology of a natural language

Computational Linguistics

Unsupervised models for morpheme segmentation and morphology learning

ACM Transactions on Speech and Language Processing (TSLP)
Learning probabilistic paradigms for morphology in a latent class model

SIGPHON '06 Proceedings of the Eighth Meeting of the ACL Special Interest Group on Computational Phonology and Morphology
A naive theory of affixation and an algorithm for extraction

SIGPHON '06 Proceedings of the Eighth Meeting of the ACL Special Interest Group on Computational Phonology and Morphology
Clustering morphological paradigms using syntactic categories

CLEF'09 Proceedings of the 10th cross-language evaluation forum conference on Multilingual information access evaluation: text retrieval experiments
Investigating the Relationship Between Linguistic Representation and Computation through an Unsupervised Model of Human Morphology Learning

Research on Language and Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

Unsupervised learning of grammar is a problem that can be important in many areas ranging from text preprocessing for information retrieval and classification to machine translation. We describe an MDL based grammar of a language that contains morphology and lexical categories. We use an unsupervised learner of morphology to bootstrap the acquisition of lexical categories and use these two learning processes iteratively to help and constrain each other. To be able to do so, we need to make our existing morphological analysis less fine grained. We present an algorithm for collapsing morphological classes (signatures) by using syntactic context. Our experiments demonstrate that this collapse preserves the relation between morphology and lexical categories within new signatures, and thereby minimizes the description length of the model.