Normal view MARC view ISBD view

Domain Dependence of Statistical Named Entity Recognition and Classification in Croatian Texts / Agić, Željko ; Bekavac, Božo.

By: Agić, Željko.
Contributor(s): Bekavac, Božo [aut].
Material type: materialTypeLabelArticleDescription: 277-283.Other title: Domain Dependence of Statistical Named Entity Recognition and Classification in Croatian Texts [Naslov na engleskom:].Subject(s): 2.09 | 5.04 | 6.03 | text domain, domain dependence, named entity recognition, Croatian language hrv | text domain, domain dependence, named entity recognition, Croatian language eng In: 35th International Conference on Information Technology Interfaces (ITI 2013) (24-27.06.2013. ; Cavtat, Hrvatska) Proceedings of the 35th International Conference on Information Technology Interfaces (ITI 2013) str. 277-283Lužar-Stiffler, Vesna ; Jarec, IvaSummary: Influence of text domain selection on statistical named entity recognition and classification in Croatian texts is investigated. Two datasets of Croatian newspaper texts of differing text domains were manually annotated for named entities and used for training and testing the Stanford NER system for named entity recognition based on sequence labeling with CRF. State of the art scores were observed in both domains. A strong preference for systems trained on mixed text domains is established by the experiment. The top- performing system was recorded with an overall F1- score of 0.876 on mixed-domain test sets, scoring 0.899 in one of the selected domains and 0.852 in the other. The single best domain F1-scores were recorded at 0.910 and 0.858.
Tags from this library: No tags from this library for this title. Log in to add tags.
No physical items for this record

Influence of text domain selection on statistical named entity recognition and classification in Croatian texts is investigated. Two datasets of Croatian newspaper texts of differing text domains were manually annotated for named entities and used for training and testing the Stanford NER system for named entity recognition based on sequence labeling with CRF. State of the art scores were observed in both domains. A strong preference for systems trained on mixed text domains is established by the experiment. The top- performing system was recorded with an overall F1- score of 0.876 on mixed-domain test sets, scoring 0.899 in one of the selected domains and 0.852 in the other. The single best domain F1-scores were recorded at 0.910 and 0.858.

Projekt MZOS 130-1300646-0645

Projekt MZOS 130-1300646-1776

ENG

There are no comments for this item.

Log in to your account to post a comment.

Powered by Koha