Named entity recognition for Hungarian using various machine learning algorithms

Farkas, Richárd and Szarvas, György and Kocsor, András: Named entity recognition for Hungarian using various machine learning algorithms. In: Acta cybernetica, (17) 3. pp. 633-646. (2006)

Cikk, tanulmány, mű

Download (163kB) | Preview


In this paper we introduce a statistical Named Entity recognizer (NER) system for the Hungarian language. We examined three methods for identifying and disambiguating proper nouns (Artificial Neural Network, Support Vector Machine, C4.5 Decision Tree), their combinations and the effects of dimensionality reduction as well. We used a segment of Szeged Corpus [5] for training and validation purposes, which consists of short business news articles collected from MTI (Hungarian News Agency, Our results were presented at the Second Conference on Hungarian Computational Linguistics [7]. Our system makes use of both language dependent features (describing the orthography of proper nouns in Hungarian) and other, language independent information such as capitalization. Since we avoided the inclusion of large gazetteers of pre-classified entities, the system remains portable across languages without requiring any major modification, as long as the few specialized orthographical and syntactic characteristics are collected for a new target language. The best performing model achieved an F measure accuracy of 91.95%.

Item Type: Article
Journal or Publication Title: Acta cybernetica
Date: 2006
Volume: 17
Number: 3
ISSN: 0324-721X
Page Range: pp. 633-646
Language: angol
Event Title: Conference on Hungarian Computational Linguistics, 2., 2004, Szeged
Uncontrolled Keywords: Természettudomány, Informatika, Nyelvtudomány
Additional Information: Bibliogr.: p. 645-646.; Abstract
Date Deposited: 2016. Oct. 15. 12:25
Last Modified: 2018. Jun. 05. 15:16

Actions (login required)

View Item View Item