Unsupervised discovery of morphemes
Published 1 January 2002Open access
Mathias Creutz, Krista Lagus
Citations362
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
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.
Abstract
We present two methods for unsupervised segmentation of words into morpheme-like units. The model utilized is especially suited for languages with a rich morphology, such as Finnish. The first method is based on the Minimum Description Length (MDL) principle and works online. In the second method, Maximum Likelihood (ML) optimization is used. The quality of the segmentations is measured using an evaluation method that compares the segmentations produced to an existing morphological analysis. Experiments on both Finnish and English corpora show that the presented methods perform well compared to a current state-of-the-art system.
Keywords
Computer Science
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
Proceedings of the IEEEExploiting latent semantic information in statistical language modeling
352 Citations2000J.R. Bellegarda
This paper focuses on the use of latent semantic analysis, a paradigm that automatically uncovers the salient semantic relationships between words and documents in a given corpus, and proposes an integrative formulation for harnessing this synergy.
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
Neural ComputationRedundancy Reduction as a Strategy for Unsupervised Learning
152 Citations1993Amanda Redlich
A local feature measure determining how much a single feature reduces the total redundancy is derived which turns out to depend only on the probability of the feature and of its components, but not on the statistical properties of any other features.
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.
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 Word Boundary with Description Length Gain
74 Citations1999Chunyu Kit, Yorick Wilks
Speech CommunicationInference of variable-length linguistic and acoustic units by multigrams
67 Citations1997Sabine Deligne, Frédéric Bimbot
A general formulation of the multigram model, applicable to single or multiple parallel strings of data having either discrete or continuous values, and used to infer a set of variable-length acoustic units, directly from speech data.
arXiv (Cornell University)The Unsupervised Acquisition of a Lexicon from Continuous Speech
61 Citations1995Carl de Marcken
An unsupervised learning algorithm is presented that acquires a natural- language lexicon from raw speech based on the optimal encoding of symbol sequences in an MDL framework, and uses a hierarchical representation of language that overcomes many of the problems that have stymied previous grammar-induction procedures.
Linguistic structure as composition and perturbation
26 Citations1996Carl de Marcken
This paper argues for a representation of language in which linguistic parameters like words are built by perturbing a composition of existing parameters, and demonstrated by several examples in text segmentation and compression, acquisition of a lexicon from raw speech, and the acquisition of mappings between text and artificial representations of meaning.
UNSUPERVISED WORD INDUCTION USING MDL CRITERION
17 Citations2000Yu Hua
A general source-coding framework for inducing words from natural language text without word boundaries is presented and an efficient search algorithm is developed to optimize the minimum description length (MDL) induction criterion.