Latent semantics in language models

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F15%3A43924529" target="_blank" >RIV/49777513:23520/15:43924529 - isvavai.cz</a>

Result on the web

<a href="http://dx.doi.org/10.1016/j.csl.2015.01.004" target="_blank" >http://dx.doi.org/10.1016/j.csl.2015.01.004</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.csl.2015.01.004" target="_blank" >10.1016/j.csl.2015.01.004</a>

Result language

angličtina

Original language name

Latent semantics in language models

Original language description

This paper investigates three different sources of information and their integration into language modelling. Global semantics is modelled by Latent Dirichlet allocation and brings long range dependencies into language models. Word clusters given by semantic spaces enrich these language models with short range semantics. Finally, our own stemming algorithm is used to further enhance the performance of language modelling for inflectional languages. Our research shows that these three sources of information enrich each other and their combination dramatically improves language modelling. All investigated models are acquired in a fully unsupervised manner. We show the efficiency of our methods for several languages such as Czech, Slovenian, Slovak, Polish, Hungarian, and English, proving their multilingualism. The perplexity tests are accompanied by machine translation tests that prove the ability of the proposed models to improve the performance of a real-world application.

Czech name

—

Czech description

—

Type

J_x - Unclassified - Peer-reviewed scientific article (Jimp, Jsc and Jost)

CEP classification

JD - Use of computers, robotics and its application

OECD FORD branch

—

Project

<a href="/en/project/ED1.1.00%2F02.0090" target="_blank" >ED1.1.00/02.0090: NTIS - New Technologies for Information Society</a><br>

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Publication year

2015

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

Computer Speech and language

ISSN

0885-2308

e-ISSN

—

Volume of the periodical

33

Issue of the periodical within the volume

1

Country of publishing house

GB - UNITED KINGDOM

Number of pages

21

Pages from-to

88-108

UT code for WoS article

—

EID of the result in the Scopus database

—