Zobrazeno 1 - 10
of 41
pro vyhledávání: '"Josef Steinberger"'
Autor:
Josef Steinberger, Pavel Přibáň
Publikováno v:
RANLP
In this paper, we aim at improving Czech sentiment with transformer-based models and their multilingual versions. More concretely, we study the task of polarity detection for the Czech language on three sentiment polarity datasets. We fine-tune and p
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0697f38ffb4684ce79191307b3f27226
https://doi.org/10.26615/978-954-452-072-4_128
https://doi.org/10.26615/978-954-452-072-4_128
Publikováno v:
RANLP
Detekce tzv. fake news a úzce souvisejícího ověřování faktů získala v poslední době velkou pozornost. Výzkum možností automatizace těchto úloh byl již částečně proveden v anglickém jazyce, ale pro ostatní jazyky existuje pouze
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0be87da47faf12f3e1d728e02ba7af27
https://doi.org/10.26615/978-954-452-056-4_113
https://doi.org/10.26615/978-954-452-056-4_113
Autor:
Roman Yangarber, Lidia Pivovarova, Jakub Piskorski, Pavel Přibáň, Michał Marcińczuk, Josef Steinberger, Laska Laskova
Publikováno v:
BSNLP@ACL
University of Helsinki
University of Helsinki
We describe the Second Multilingual Named Entity Challenge in Slavic languages. The task is recognizing mentions of named entities in Web documents, their normalization, and cross-lingual linking The Challenge was organized as part of the 7th Balto-S
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::661bb7db6d9743f9551e107e7cf2d975
https://doi.org/10.18653/v1/w19-3709
https://doi.org/10.18653/v1/w19-3709
Publikováno v:
SemEval@NAACL-HLT
We present our UWB system for the task of capturing discriminative attributes at SemEval 2018. Given two words and an attribute, the system decides, whether this attribute is discriminative between the words or not. Assuming Distributional Hypothesis
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a912674e455b1bbd04a25387e64338c9
https://doi.org/10.18653/v1/s18-1153
https://doi.org/10.18653/v1/s18-1153
Publikováno v:
Information Processing & Management. 51:532-546
We explore state-of-the-art supervised machine learning methods for sentiment analysis of Czech social media.We provide a large human-annotated Czech social media corpus.We explore different pre-processing techniques and employ various features and c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ea66c34d819bac6a6d49170706a0304d
https://doi.org/10.1016/j.ipm.2015.05.006
https://doi.org/10.1016/j.ipm.2015.05.006
Publikováno v:
RANLP
We introduce Flames Detector, an online system for measuring flames, i.e. strong negative feelings or emotions, insults or other verbal offences, in news commentaries across five languages. It is designed to assist journalists, public institutions or
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7c5ba66f0fec77bd948bb233ea2ae424
https://doi.org/10.26615/978-954-452-049-6_089
https://doi.org/10.26615/978-954-452-049-6_089
Autor:
George Giannakopoulos, Peter A. Rankel, Marina Litvak, Josef Steinberger, John M. Conroy, Elena Lloret, Jeff Kubina, Benoit Favre
Publikováno v:
MultiLing@EACL
In this brief report we present an overview of the MultiLing 2017 effort and workshop, as implemented within EACL 2017. MultiLing is a community-driven initiative that pushes the state-of-the-art in Automatic Summarization by providing data sets and
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ece232f1ed7dc9cf45bf1c5c010cf6cf
https://doi.org/10.18653/v1/w17-1001
https://doi.org/10.18653/v1/w17-1001
Publikováno v:
University of Helsinki
BSNLP@EACL
BSNLP@EACL
This paper describes the outcomes of the first challenge on multilingual named entity recognition that aimed at recognizing mentions of named entities in web documents in Slavic languages, their normalization/lemmatization, and cross-language matchin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3e3653ef803bf3d940629b2e5f772315
http://hdl.handle.net/10138/215622
http://hdl.handle.net/10138/215622
Publikováno v:
Information Processing & Management. 50:693-707
This article describes in-depth research on machine learning methods for sentiment analysis of Czech social media. Whereas in English, Chinese, or Spanish this field has a long history and evaluation datasets for various domains are widely available,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ffe44cb63e75a15ac70ea727a5236eeb
https://doi.org/10.1016/j.ipm.2014.05.001
https://doi.org/10.1016/j.ipm.2014.05.001
Autor:
Yuqiao Gu, Fabio Celli, Josef Steinberger, Andrew James Anderson, Massimo Poesio, Carlo Strapparava, Brian Murphy
Publikováno v:
Journal for Language Technology and Computational Linguistics. 29:79-94
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d26b6af132dda96613fd36a5eccc77ae
https://doi.org/10.21248/jlcl.29.2014.185
https://doi.org/10.21248/jlcl.29.2014.185