Full text
Preview |
PDF
- Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (957kB) | Preview |
Villena Román, Julio and Lana Serrano, Sara and González Cristóbal, José Carlos (2008). MIRACLE at NTCIR-7 MOAT: First experiments on multilingual opinion analysis. In: "7th NTCIR Workshop Meeting on Evaluation of Information Access Technologies", 16/12/2008-19/12/2008, Tokyo, Japón. ISBN 9784860490447.
Title: | MIRACLE at NTCIR-7 MOAT: First experiments on multilingual opinion analysis |
---|---|
Author/s: |
|
Item Type: | Presentation at Congress or Conference (Article) |
Event Title: | 7th NTCIR Workshop Meeting on Evaluation of Information Access Technologies |
Event Dates: | 16/12/2008-19/12/2008 |
Event Location: | Tokyo, Japón |
Title of Book: | Proceedings of 7th NTCIR Workshop Meeting on Evaluation of Information Access Technologies |
Date: | 2008 |
ISBN: | 9784860490447 |
Subjects: | |
Freetext Keywords: | NTCIR, MIRACLE, Multilingual Opinion Analysis Task, semantic tagging, statistical approach. |
Faculty: | E.U.I.T. Telecomunicación (UPM) |
Department: | Ingeniería y Arquitecturas Telemáticas [hasta 2014] |
Creative Commons Licenses: | Recognition - No derivative works - Non commercial |
Preview |
PDF
- Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (957kB) | Preview |
This paper describes the participation of MIRACLE research consortium at NTCIR-7 Multilingual Opinion Analysis Task, our first attempt on sentiment analysis and second on East Asian languages. We took part in the main mandatory opinionated sentence judgment subtask (to decide whether each sentence expresses an opinion or not) and the optional relevance and polarity judgment subtasks (to decide whether a given sentence is relevant to the given topic and also the polarity of the expressed opinion). Our approach combines a semantic languagedependent tagging of the terms of the sentence and the topic and three different ad-hoc classifiers that provide the specific annotation for each subtask, run in cascade. These models have been trained with the corpus provided in NTCIR-6 Opinion Analysis pilot task.
Item ID: | 4347 |
---|---|
DC Identifier: | https://oa.upm.es/4347/ |
OAI Identifier: | oai:oa.upm.es:4347 |
Official URL: | http://research.nii.ac.jp/ntcir/workshop/OnlinePro... |
Deposited by: | Memoria Investigacion |
Deposited on: | 23 Sep 2010 11:29 |
Last Modified: | 20 Apr 2016 13:36 |