Title: UWB at SemEval 2014 and 2016
Authors: Brychcín, Tomáš
Hercig, Tomáš
Svoboda, Lukáš
Konkol, Michal
Citation: STEINBERGER, Josef ed.; ZÍMA, Martin ed.; FIALA, Dalibor ed.; DOSTAL, Martin ed.; NYKL, Michal ed. Data a znalosti 2017: sborník konference, Plzeň, Hotel Angelo 5. - 6. října 2017. 1. vyd. Plzeň: Západočeská univerzita v Plzni, 2017, s. 111-115. ISBN 978-80-261-0720-0.
Issue Date: 2017
Publisher: Západočeská univerzita v Plzni
Document type: konferenční příspěvek
URI: https://www.zcu.cz/export/sites/zcu/pracoviste/vyd/online/DataAZnalosti2017.pdf
ISBN: 978-80-261-0720-0
Keywords: SemEval;sémantická textová podobnost;aspektová analýza sentimentu;distribuční sémantika
Keywords in different language: SemEval;semantic textual similarity;aspect-based sentiment analysis;distributional semantics
Abstract in different language: International Workshop on Semantic Evaluation (SemEval) is an on-going series of evaluations of NLP (Natural Language Processing) algorithms, organized by Association for Computational Linguistics (ACL), the internation-al scientific society which hold the major NLP conferences. The evaluations are intended to explore different aspects of meaning in a natural language. The re-sults of NLP algorithms are compared with human judgments. The submitted systems from research teams across the world are compared in terms of perfor-mance. Our research team actively participates in the SemEval exercises. This paper summarizes our results in the area of semantic textual similarity and as-pect-based sentiment analysis. In 2014 and 2016 our systems were among the best performing in both mentioned tasks.
Rights: © Západočeská univerzita v Plzni
Appears in Collections:Konferenční příspěvky / Conference Papers (KIV)
Konferenční příspěvky / Conference papers (NTIS)
Data a znalosti 2017
Data a znalosti 2017

Files in This Item:
File Description SizeFormat 
Brychcin.pdfPlný text404,35 kBAdobe PDFView/Open

Please use this identifier to cite or link to this item: http://hdl.handle.net/11025/26346

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.