Demonstration venue · read-only. Every page can be browsed; the buttons that would change it are switched off. Create an account to run TaxoReview on your own data. A simulation from public publication records: the people listed were not invited and did not agree to review.
? Tutorial for this page

Jirí Havelka

dblp:29/2187 · DBLP profile ↗
← Back
9ranked-venue papers
1as first author
0since 2021 · last 2017
—ORCID · none

Domains — the database's venue-derived domains; a paper can count in several

Artificial intelligence and machine learning · 9 · 1 first-authorDatabases, data management, data science and information retrieval · 1

Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.

Artificial intelligence
2 papers
Information extraction and text analysis · 94% Language models and text generation · 6%
Theoretical computer science
1 paper
Graph algorithms and graph theory · 100%

Topics — the 4 heaviest of 5, each with the papers that count most for it

TopicWeightPapersLastEvidence papers
Natural language and speech › Information extraction and text analysis › syntactic parsing › dependency parsing
non-projective dependency parsing
0.122007
Log-Linear Models of Non-Projective Trees, $k$-best MST Parsing and Tree-Ranking · EMNLP-CoNLL 2007
Beyond Projectivity: Multilingual Evaluation of Constraints and Measures on Non-Projective Structures · ACL 2007
Natural language and speech › Information extraction and text analysis
syntactic parsing
0.122007
Log-Linear Models of Non-Projective Trees, $k$-best MST Parsing and Tree-Ranking · EMNLP-CoNLL 2007
Beyond Projectivity: Multilingual Evaluation of Constraints and Measures on Non-Projective Structures · ACL 2007
Graph algorithms and graph theory › spanning tree
minimum spanning tree
0.112007
Log-Linear Models of Non-Projective Trees, $k$-best MST Parsing and Tree-Ranking · EMNLP-CoNLL 2007
Natural language and speech › Language models and text generation › evaluation of language models
multilingual evaluation
0.012007
Beyond Projectivity: Multilingual Evaluation of Constraints and Measures on Non-Projective Structures · ACL 2007

Methods — techniques the papers use, named apart from their topics

log-linear model · 0.1k-best MST parsing · 0.1
YearPublicationVenuePosition
2017 Malware Detection by Analysing Encrypted Network Traffic with Neural Networks
Paul Prasse, Lukás Machlica, Tomás Pevný, Jirí Havelka, Tobias Scheffer
ECML/PKDD (2)4
2007 Beyond Projectivity: Multilingual Evaluation of Constraints and Measures on Non-Projective Structures
Jirí Havelka
ACL1
2007 Log-Linear Models of Non-Projective Trees, $k$-best MST Parsing and Tree-Ranking
Keith B. Hall, Jirí Havelka, David A. Smith
EMNLP-CoNLL2
2005 Prague Czech-English dependency treebank: resource for structure-based MT
Martin Cmejrek, Jan Curín, Jan Hajic 0001, Jirí Havelka
EAMT4
2004 Condition of Projectivity in the Underlying Dependency Structures
abstract
The claim made in this paper is that in a formal description of language, it is possible and useful to work with dependency-based underlying representations of sentences (tectogrammatical representations) meeting the condition of projectivity. The reasons for the inclusion of this condition into the definition of the tectogrammatical representations are both formally and empirically sound (Section 1). An analysis of the material offered by the Prague Dependency Treebank with annotations of the underlying syntactic structure of sentences (described in Section 2) has led to an interesting classification of non-projective constructions in Czech (Section 3). It documents that most (types of) constructions that appear to be non-projective in the surface shape of sentences can be described by means of projective trees. The realization of the surface word order (with the use of movement rules) is then relegated to the morphemic level, where the representation of the sentence has the shape of a string rather than a tree.
Katerina Vesela, Jirí Havelka, Eva Hajicová
COLING2
2004 Building a Parallel Bilingual Syntactically Annotated Corpus
Jan Curín, Martin Cmejrek, Jirí Havelka, Vladislav Kubon
IJCNLP3
2004 Prague Czech-English Dependency Treebank. Syntactically Annotated Resources for Machine Translation
Martin Cmejrek, Jan Curín, Jirí Havelka, Jan Hajic 0001, Vladislav Kubon
LREC3
2004 Annotators' Agreement: The Case of Topic-Focus Articulation
Katerina Vesela, Jirí Havelka, Eva Hajicová
LREC2
2003 Czech-English Dependency Tree-based Machine Translation
Martin Cmejrek, Jan Curín, Jirí Havelka
EACL3