Semantic Space Transformations for Cross-Lingual Document Classification

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F18%3A43952471" target="_blank" >RIV/49777513:23520/18:43952471 - isvavai.cz</a>

Result on the web

<a href="http://dx.doi.org/10.1007/978-3-030-01418-6_60" target="_blank" >http://dx.doi.org/10.1007/978-3-030-01418-6_60</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-030-01418-6_60" target="_blank" >10.1007/978-3-030-01418-6_60</a>

Result language

angličtina

Original language name

Semantic Space Transformations for Cross-Lingual Document Classification

Original language description

This paper deals with cross-lingual document classification. Cross-linguality is achieved by training monolingual semantic spaces and then using a transform method to project word vectors into a unified space. The main goal of this paper consists in the evaluation of three promising transform methods utilized for this task. Convolutional neural network (CNN) classifier is used and its performance is compared with a standard maximum entropy classifier. The proposed methods are evaluated on four languages, namely English, German, Spanish and Italian from the Reuters corpus. It is shown that the results of all transformation methods are close to each other, however the orthogonal transformation gives generally slightly better results when CNN with trained embeddings is used. The experimental results also show that convolutional network achieves better results than maximum entropy classifier.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

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

Project

<a href="/en/project/LO1506" target="_blank" >LO1506: Sustainability support of the centre NTIS - New Technologies for the 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

2018

Confidentiality

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

Article name in the collection

Artificial Neural Networks and Machine Learning – ICANN 2018

ISBN

978-3-030-01417-9

ISSN

0302-9743

e-ISSN

1611-3349

Number of pages

9

Pages from-to

608-616

Publisher name

Springer

Place of publication

Cham

Event location

Rhodos, Řecko

Event date

Oct 4, 2018

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—