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
Demo Data from VLDB 2026 / reviewers in the wild / expert

Daniel Kondratyuk

dblp:225/4606 · DBLP profile ↗
← Back
2ranked-venue papers
2as first author
0since 2021 · last 2019
—ORCID · none

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

Artificial intelligence and machine learning · 2 · 2 first-author

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 · 90% Language models and text generation · 10%

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

TopicWeightPapersLastEvidence papers
Natural language and speech › Information extraction and text analysis › syntactic parsing
dependency parsing		 0.412019
75 Languages, 1 Model: Parsing Universal Dependencies Universally · EMNLP/IJCNLP (1) 2019
Natural language and speech › Information extraction and text analysis › morphological analysis
lemmatization		 0.312018
LemmaTag: Jointly Tagging and Lemmatizing for Morphologically Rich Languages with BRNNs · EMNLP 2018
Natural language and speech › Information extraction and text analysis › sequence labeling
part-of-speech tagging		 0.312018
LemmaTag: Jointly Tagging and Lemmatizing for Morphologically Rich Languages with BRNNs · EMNLP 2018
Natural language and speech › Language models and text generation
multilingual language models		 0.112019
75 Languages, 1 Model: Parsing Universal Dependencies Universally · EMNLP/IJCNLP (1) 2019

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

universal dependency parsing · 0.4multilingual model · 0.4word-level embedding · 0.3character-level embedding · 0.3bidirectional recurrent neural network · 0.3
YearPublicationVenuePosition
2019 75 Languages, 1 Model: Parsing Universal Dependencies Universally
abstract
Dan Kondratyuk, Milan Straka. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.
Daniel Kondratyuk, Milan Straka
 EMNLP/IJCNLP (1)1
2018 LemmaTag: Jointly Tagging and Lemmatizing for Morphologically Rich Languages with BRNNs
abstract
We present LemmaTag, a featureless neural network architecture that jointly generates part-of-speech tags and lemmas for sentences by using bidirectional RNNs with characterlevel and word-level embeddings.We demonstrate that both tasks benefit from sharing the encoding part of the network, predicting tag subcategories, and using the tagger output as an input to the lemmatizer.We evaluate our model across several languages with complex morphology, which surpasses state-of-the-art accuracy in both part-of-speech tagging and lemmatization in Czech, German, and Arabic.
Daniel Kondratyuk, Tomas Gavenciak, Milan Straka, Jan Hajic 0001
 EMNLP1