Towards Multilingual Event Extraction Evaluation: A Case Study for the Czech Language

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F15%3A43927662" target="_blank" >RIV/49777513:23520/15:43927662 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Towards Multilingual Event Extraction Evaluation: A Case Study for the Czech Language

Popis výsledku v původním jazyce

This paper presents a multilingual corpus of news, annotated with event metadata information. The events in our corpus are from the domain of violence, natural and man-made disasters. The main goal of the corpus is automatic evaluation of event detectionand extraction systems in different languages. As a use case, we take a rule-based event extraction system, extend it to cover a new language, Czech in our case, and evaluate it on the corpus. We explain what needs to be done to cover a new language, especially learning domain-specific dictionaries and event extraction patterns. The evaluation of the Czech system can be viewed as a starting point for further research into the evaluation of multilingual event extraction systems, which is an important stage during the development of such systems. The comparison of the performance for the Czech and English systems indicates the importance for multilingual event extraction evaluation

Název v anglickém jazyce

Towards Multilingual Event Extraction Evaluation: A Case Study for the Czech Language

Popis výsledku anglicky

This paper presents a multilingual corpus of news, annotated with event metadata information. The events in our corpus are from the domain of violence, natural and man-made disasters. The main goal of the corpus is automatic evaluation of event detectionand extraction systems in different languages. As a use case, we take a rule-based event extraction system, extend it to cover a new language, Czech in our case, and evaluate it on the corpus. We explain what needs to be done to cover a new language, especially learning domain-specific dictionaries and event extraction patterns. The evaluation of the Czech system can be viewed as a starting point for further research into the evaluation of multilingual event extraction systems, which is an important stage during the development of such systems. The comparison of the performance for the Czech and English systems indicates the importance for multilingual event extraction evaluation

Druh

D - Stať ve sborníku

CEP obor

IN - Informatika

OECD FORD obor

—

Projekt

—

Návaznosti

R - Projekt Ramcoveho programu EK

Rok uplatnění

2015

Kód důvěrnosti údajů

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

Název statě ve sborníku

PROCEEDINGS OF THE INTERNATIONAL CONFERENCE RECENT ADVANCES IN NATURAL LANGUAGE PROCESSING'2015

ISBN

—

ISSN

1313-8502

e-ISSN

—

Počet stran výsledku

9

Strana od-do

627-635

Název nakladatele

INCOMA Ltd.

Místo vydání

Shoumen, Bulgaria

Místo konání akce

hissar, Bulharsko

Datum konání akce

7. 9. 2015

Typ akce podle státní příslušnosti

EUR - Evropská akce

Kód UT WoS článku

—