Induction of a simple morphology for highly-inflecting languages
Published 1 January 2004Open access
Mathias Creutz, Krista Lagus
Citations54
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
An algorithm for the unsupervised learning of a simple morphology of a natural language from raw text using a generative probabilistic model to segment word forms into morphs, which makes the model suitable for highly-inflecting languages.
Abstract
This paper presents an algorithm for the unsupervised learning of a simple morphology of a natural language from raw text. A generative probabilistic model is applied to segment word forms into morphs. The morphs are assumed to be generated by one of three categories, namely prefix, suffix, or stem, and we make use of some observed asymmetries between these categories. The model learns a word structure, where words are allowed to consist of lengthy sequences of alternating stems and affixes, which makes the model suitable for highly-inflecting languages. The ability of the algorithm to find real morpheme boundaries is evaluated against a gold standard for both Finnish and English. In comparison with a state-of-the-art algorithm the new algorithm performs best on the Finnish data, and on roughly equal level on the English data.
Keywords
Computer Science
Journal of Memory and LanguageWord Segmentation: The Role of Distributional Cues
1,409 Citations1996Jenny R. Saffran, Elissa L. Newport +1 more
Computational LinguisticsUnsupervised Learning of the Morphology of a Natural Language
797 Citations2001John Goldsmith
This study reports the results of using minimum description length (MDL) analysis to model unsupervised learning of the morphological segmentation of European languages, using corpora ranging in size from 5,000 Words to 500,000 words.
Helda (University of Helsinki)Two-Level Morphology: A General Computational Model for Word-Form Recognition and Production
792 Citations1983Kimmo Koskenniemi
Unsupervised discovery of morphemes
362 Citations2002Mathias Creutz, Krista Lagus
Two methods for unsupervised segmentation of words into morpheme-like units are presented based on the Minimum Description Length (MDL) principle and Maximum Likelihood (ML) optimization is used.
Machine LearningAn Efficient, Probabilistically Sound Algorithm for Segmentation and Word Discovery
289 Citations1999Michael R. Brent
Experiments on phonemic transcripts of spontaneous speech by parents to young children suggest that the model-based, unsupervised algorithm for recovering word boundaries in a natural-language text from which they have been deleted is more effective than other proposed algorithms, at least when utterance boundaries are given and the text includes a substantial number of short utterances.
arXiv (Cornell University)An Efficient, Probabilistically Sound Algorithm for Segmentation and Word Discovery
208 Citations1999Michael R. Brent
Minimally supervised morphological analysis by multimodal alignment
188 Citations2000David Yarowsky, Richard Wicentowski
A corpus-based algorithm capable of inducing inflectional morphological analyses of both regular and highly irregular forms from distributional patterns in large monolingual text with no direct supervision is presented.
arXiv (Cornell University)Unsupervised Language Acquisition
129 Citations1996Carl G. de Marcken
The thesis introduces a variety of technical innovations, among them a common representation for evidence and grammars that has many linguistically and statistically desirable properties, and a learning strategy that separates the "content" of linguistic parameters from their representation.
Knowledge-free induction of inflectional morphologies
120 Citations2001Patrick Schone, Daniel Jurafsky
An algorithm to automatically induce the morphology of inflectional languages using only text corpora and no human input is proposed, showing it to be an improvement over any knowledge-free algorithm yet proposed.
Knowledge-free induction of morphology using latent semantic analysis
114 Citations2000Patrick Schone, Daniel Jurafsky
A semantics-only algorithm for learning morphology which only proposes affixes when the stem and stem-plus-affix are sufficiently similar semantically and it is shown that this approach provides morphology induction results that rival a current state-of-the-art system.
Unsupervised discovery of morphologically related words based on orthographic and semantic similarity
114 Citations2002Marco Baroni, Johannes Matiasek +1 more
An algorithm that takes an unannotated corpus as its input, and returns a ranked list of probable morphologically related pairs as its output, giving encouraging results in terms of precision and qualitative analysis of the types of morphological patterns discovered by the algorithm.
Morphemes as necessary concept for structures discovery from untagged corpora
79 Citations1998Hervé Déjean
An overview of a method which allows discovery of syntactic structures from untagged corpora, composed of the discovery of the grammatical morphemes of the language, and the procedure of correction which required the chunk level.
Unsupervised learning of morphology without morphemes
74 Citations2002Sylvain Neuvel, Sean A. Fulop
The first morphological learner based upon the theory of Whole Word Morphology (Ford et al., 1997) is outlined, and preliminary evaluation results are presented.
Unsupervised segmentation of words using prior distributions of morph length and frequency
73 Citations2003Mathias Creutz
This work presents a language-independent and unsupervised algorithm for the segmentation of words into morphs, based on a new generative probabilistic model, which makes use of relevant prior information on the length and frequency distributions of morphs in a language.
Unlimited vocabulary speech recognition based on morphs discovered in an unsupervised manner
65 Citations2003Vesa Siivola, Teemu Hirsimäki +2 more
A method based on the Minimum Description Length principle is used to split words statistically into subword units allowing efficient language modeling and unlimited vocabulary and the resulting model outperforms both word and syllable based trigram models.
On lexicon creation for turkish LVCSR
51 Citations2003Kadri Hacıoğlu, Bryan Pellom +4 more
This paper addresses the lexicon design problem in Turkish large vocabulary speech recognition using morphology-based and data-driven methods and presents experimental results that show the methods are very effective to lower the word error rate at the expense of lexicon size.
A Bayesian model for morpheme and paradigm identification
48 Citations2001Matthew Snover, Michael R. Brent
A system for unsupervised learning of morphological affixes from texts or word lists composed of a generative probability model and a search algorithm that can be formalized in terms of the lattice formed by subsets of suffixes under inclusion.