Enriching Word Embeddings with Global Information and Testing on Highly Inflected language

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F19%3A43956619" target="_blank" >RIV/49777513:23520/19:43956619 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.cys.cic.ipn.mx/ojs/index.php/CyS/article/view/3268" target="_blank" >https://www.cys.cic.ipn.mx/ojs/index.php/CyS/article/view/3268</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.13053/CyS-23-3-3268" target="_blank" >10.13053/CyS-23-3-3268</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Enriching Word Embeddings with Global Information and Testing on Highly Inflected language

Popis výsledku v původním jazyce

In this paper we evaluate our new approach based on the Continuous Bag-of-Words and Skip-gram models enriched with global context information on highly inflected Czech language and compare it with English results. As a source of information we use Wikipedia, where articles are organized in a hierarchy of categories. These categories provide useful topical information about each article. Both models are evaluated on standard word similarity and word analogy datasets. Proposed models outperform other word representation methods when similar size of training data is used. Model provide similar performance especially with methods trained on much larger datasets.

Název v anglickém jazyce

Enriching Word Embeddings with Global Information and Testing on Highly Inflected language

Popis výsledku anglicky

In this paper we evaluate our new approach based on the Continuous Bag-of-Words and Skip-gram models enriched with global context information on highly inflected Czech language and compare it with English results. As a source of information we use Wikipedia, where articles are organized in a hierarchy of categories. These categories provide useful topical information about each article. Both models are evaluated on standard word similarity and word analogy datasets. Proposed models outperform other word representation methods when similar size of training data is used. Model provide similar performance especially with methods trained on much larger datasets.

Druh

J_SC - Článek v periodiku v databázi SCOPUS

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2019

Kód důvěrnosti údajů

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

Název periodika

Computación y Systemas

ISSN

1405-5546

e-ISSN

—

Svazek periodika

23

Číslo periodika v rámci svazku

3

Stát vydavatele periodika

MX - Spojené státy mexické

Počet stran výsledku

11

Strana od-do

773-783

Kód UT WoS článku

—

EID výsledku v databázi Scopus

2-s2.0-85076634219