Corpus ID: 14886349

Unsupervised Morpheme Segmentation and Morphology Induction from Text Corpora Using Morfessor 1.0

@inproceedings{Creutz2005UnsupervisedMS,
  title={Unsupervised Morpheme Segmentation and Morphology Induction from Text Corpora Using Morfessor 1.0},
  author={Mathias Creutz and Krista Lagus},
  year={2005}
}
  • Mathias Creutz, Krista Lagus
  • Published 2005
  • Computer Science
  • In this work, we describe the first public version of the Morfessor software, which is a program that takes as input a corpus of unannotated text and produces a segmentation of the word forms observed in the text. The segmentation obtained often resembles a linguistic morpheme segmentation. Morfessor is not language-dependent. The number of segments per word is not restricted to two or three as in some other existing morphology learning models. The current version of the software essentially… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 249 CITATIONS

    Stemming resource-poor Indian languages

    VIEW 16 EXCERPTS
    CITES RESULTS, BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Morpheme Level Feature-based Language Models for German LVCSR

    VIEW 5 EXCERPTS
    CITES METHODS
    HIGHLY INFLUENCED

    Unsupervised Morphological Word Clustering

    VIEW 12 EXCERPTS
    CITES BACKGROUND, METHODS & RESULTS
    HIGHLY INFLUENCED

    Diplomarbeit Unsupervised Morpheme Segmentation using Formal Analogies

    VIEW 8 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Applying Morphological Decompositions to Statistical Machine Translation

    VIEW 10 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Morphology-based language modeling for amharic

    VIEW 7 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Analysis of the recognition errors in LVCSR of Turkish

    VIEW 4 EXCERPTS
    CITES METHODS
    HIGHLY INFLUENCED

    FILTER CITATIONS BY YEAR

    2005
    2020

    CITATION STATISTICS

    • 50 Highly Influenced Citations

    • Averaged 12 Citations per year from 2017 through 2019

    References

    Publications referenced by this paper.