no code implementations • SEMEVAL 2018 • Tom{\'a}{\v{s}} Brychc{\'\i}n, Tom{\'a}{\v{s}} Hercig, Josef Steinberger, Michal Konkol
We show the word distribution in the corpus has potential for detecting discriminative attributes.
Ranked #4 on Relation Extraction on SemEval 2018 Task 10
no code implementations • IJCNLP 2017 • Michal Konkol, Tom{\'a}{\v{s}} Brychc{\'\i}n, Michal Nykl, Tom{\'a}{\v{s}} Hercig
We implement this principle by comparing the information in the word embeddings with geographical positions of cities.
no code implementations • RANLP 2017 • Josef Steinberger, Tom{\'a}{\v{s}} Brychc{\'\i}n, Tom{\'a}{\v{s}} Hercig, Peter Krejzl
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.
no code implementations • RANLP 2017 • Josef Steinberger, Peter Krejzl, Tom{\'a}{\v{s}} Brychc{\'\i}n
We propose a novel metric for evaluating summary content coverage.
no code implementations • EACL 2017 • Tom{\'a}{\v{s}} Brychc{\'\i}n, Pavel Kr{\'a}l
This paper introduces a new unsupervised approach for dialogue act induction.