Modelling highly inflected languages

DOI10.1016/J.INS.2003.12.004MaRDI QIDQ1886781zbMATH OpenOpenAlexFDO

Authors Mirjam Sepesy Maučec, Zdravko Kačič, Bogomir Horvat

Publication date 19 November 2004

Published in Information Sciences (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.ins.2003.12.004

zbMATH Keywords

Approximate string matchingMixture-based modelPerplexityStatistical language modellingTopic similarityVector-space retrieval model

Mathematics Subject Classification ID

Natural language processing (68T50)

Recommendations

• A framework for linguistic modelling
• Incorporating linguistic structure into statistical language models
• Modeling language evolution
• Linguistic modeling with hierarchical systems of weighted linguistic rules

Cites work

• scientific article; zbMATH DE number 1408945 (Why is no real title available?)
• A Mathematical Theory of Communication
• Extraction and representation of contextual information for knowledge discovery in texts
• On scale and concentration invariance in entropies.

Cited in

(7)

• A framework for linguistic modelling
• Smoothed class-based \(n\)-gram model for recognition of the Slavic languages
• Utilizing vector models for automatic text lemmatization
• Parallel comparison of run-length-encoded strings on a linear systolic array
• Reduction of morpho-syntactic features in statistical machine translation of highly inflective language
• Cache-based statistical language models of English and highly inflected Lithuanian
• On principal component analysis, cosine and Euclidean measures in information retrieval

Describes a project that uses

Uses Software

• CMU

This page was built for publication: Modelling highly inflected languages

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1886781)