Multilingual opinion holder and target extraction using knowledge-poor techniques

Zagibalov, Taras and Carroll, John (2009) Multilingual opinion holder and target extraction using knowledge-poor techniques. In: Proceedings of the 4th Language and Technology Conference (LTC), Poznań, Poland..

Full text not available from this repository.

Abstract

We describe an approach to multilingual sentiment analysis, in particular opinion holder and opinion target extraction, wich requires no annotated data and minimal language-specific input. The approach is based on un supervised, knowledge-poor techniques wich facilitate adaptation to new languages and domains. The system's result are comparable to those of supervised, languaje-specific systems previously applied to the NTCIR-7 MOAT evaluation data.

Item Type: Conference or Workshop Item (Paper)
Schools and Departments: School of Engineering and Informatics > Informatics
Subjects: T Technology
Related URLs:
Depositing User: Juan Loera Gonzalez
Date Deposited: 24 Apr 2012 10:37
Last Modified: 24 Apr 2012 10:37
URI: http://sro.sussex.ac.uk/id/eprint/38702
📧 Request an update