Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Towards semi-supervised Brazilian Portuguese semantic role labeling: Building a benchmark

Alva Manchego, Fernando Emilio and Rosa, João Luís G. 2012. Towards semi-supervised Brazilian Portuguese semantic role labeling: Building a benchmark. Presented at: PROPOR: International Conference on Computational Processing of the Portuguese Language, 17-20 April 2012. Published in: Caseli, Helena, Villavicencio, Aline, Teixera, Antonio and Perdigao, Fernando eds. Computational Processing of the Portuguese Language: 10th International Conference, PROPOR 2012, Coimbra, Portugal, April 17-20, 2012. Proceedings. Springer, pp. 210-217. 10.1007/978-3-642-28885-2_24

Full text not available from this repository.


One of the main research challenges in semantic role labeling (SRL) is the development of applications for languages other than English. For Brazilian Portuguese, recent projects in lexical semantics are about to provide the necessary computational resources for research in this area. However, the amount of annotated data provided is not significant enough for successful supervised learning. Hence, we propose to use a semi-supervised approach capable of taking advantage of both annotated and unannotated data available. In this paper, we outline the methodology for the development of this SRL system, the same as the benchmark to be used to test its performance.

Item Type: Conference or Workshop Item (Paper)
Status: Published
Schools: Computer Science & Informatics
Publisher: Springer
ISBN: 9783642288845
ISSN: 0302-9743
Last Modified: 04 Apr 2022 10:00

Citation Data

Cited 2 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item Edit Item