Named Entity Recognition in Vietnamese Tweets

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27240%2F15%3A86096567" target="_blank" >RIV/61989100:27240/15:86096567 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1007/978-3-319-21786-4_18" target="_blank" >http://dx.doi.org/10.1007/978-3-319-21786-4_18</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-319-21786-4_18" target="_blank" >10.1007/978-3-319-21786-4_18</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Named Entity Recognition in Vietnamese Tweets

Popis výsledku v původním jazyce

Named entity recognition (NER) is a task of detecting named entities in documents and categorizing them to predefined classes such as Person (PER), Location (LOC), Organization (ORG) and so on. There have been many approaches proposed to tackle this problem in both formal texts such as news or authorized web content and short texts such as contents in online social network. However, those texts were written in languages other than Vietnamese. In this paper, we propose a method for NER in Vietnamese tweets. Since tweets on Twitter are noisy, irregular, short and consist of acronyms, spelling errors, NER in those tweets is a challenging task. Our method firstly normalizes tweets and then applies a learning model to recognize named entities using six different types of features. We built a training set of more than 40,000 named entities, and a testing set of 2,446 named entities to evaluate our system. The experiment results show that our system achieves encouraging performance with 82.3%

Název v anglickém jazyce

Named Entity Recognition in Vietnamese Tweets

Popis výsledku anglicky

Named entity recognition (NER) is a task of detecting named entities in documents and categorizing them to predefined classes such as Person (PER), Location (LOC), Organization (ORG) and so on. There have been many approaches proposed to tackle this problem in both formal texts such as news or authorized web content and short texts such as contents in online social network. However, those texts were written in languages other than Vietnamese. In this paper, we propose a method for NER in Vietnamese tweets. Since tweets on Twitter are noisy, irregular, short and consist of acronyms, spelling errors, NER in those tweets is a challenging task. Our method firstly normalizes tweets and then applies a learning model to recognize named entities using six different types of features. We built a training set of more than 40,000 named entities, and a testing set of 2,446 named entities to evaluate our system. The experiment results show that our system achieves encouraging performance with 82.3%

Druh

D - Stať ve sborníku

CEP obor

IN - Informatika

OECD FORD obor

—

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2015

Kód důvěrnosti údajů

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

Název statě ve sborníku

Lecture Notes in Computer Science. Volume 9197

ISBN

978-3-319-21785-7

ISSN

0302-9743

e-ISSN

—

Počet stran výsledku

11

Strana od-do

205-215

Název nakladatele

Springer Verlag

Místo vydání

London

Místo konání akce

Beijing

Datum konání akce

4. 8. 2015

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—