One System to Solve Them All

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14330%2F14%3A00077509" target="_blank" >RIV/00216224:14330/14:00077509 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
One System to Solve Them All
Original language description
People are daily confronted with hundreds of situations in which they could use the knowledge of stylometry. In this paper, I propose a universal system to solve these situations using stylometry features, machine learning techniques and nature languageprocessing tools. The proposed tool can help translation companies to recognize machine translation falsely submitted as a work of a human expert; identify school essays not written by the underwritten student; or cluster product reviews by authors and merge user reviews written by one author using multiple accounts. All examples above use same techniques and procedures to solve the problem, therefore it is preferred to merge algorithms and implementation of these tasks to a single framework
Czech name
—
Czech description
—

Project
<a href="/en/project/LM2010013" target="_blank" >LM2010013: LINDAT-CLARIN: Institute for analysis, processing and distribution of linguistic data</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
2014
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Eighth Workshop on Recent Advances in Slavonic Natural Language Processing
ISBN
—
ISSN
2336-4289
e-ISSN
—
Number of pages
8
Pages from-to
19-26
Publisher name
Tribun EU
Place of publication
Brno
Event location
Brno
Event date
Jan 1, 2014
Type of event by nationality
CST - Celostátní akce
UT code for WoS article
—

Similar results(10)