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

Pavel Petrushkov

dblp:205/2696 · DBLP profile ↗
← Back
2ranked-venue papers
0as 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

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
Machine translation · 56% Transfer learning and domain adaptation · 25% Planning, search and constraint satisfaction · 19%

Topics — the 5 heaviest of 6, each with the papers that count most for it

TopicWeightPapersLastEvidence papers
Machine learning › Transfer learning and domain adaptation
cross-lingual transfer		 0.412019
Pivot-based Transfer Learning for Neural Machine Translation between Non-English Languages · EMNLP/IJCNLP (1) 2019
Knowledge, reasoning and agents › Planning, search and constraint satisfaction
hybrid search		 0.312017
Neural Machine Translation Leveraging Phrase-based Models in a Hybrid Search · EMNLP 2017
Natural language and speech › Machine translation
neural machine translation		 0.312017
Neural Machine Translation Leveraging Phrase-based Models in a Hybrid Search · EMNLP 2017
Natural language and speech › Machine translation › statistical machine translation
phrase-based translation		 0.112017
Neural Machine Translation Leveraging Phrase-based Models in a Hybrid Search · EMNLP 2017
Natural language and speech › Machine translation
statistical machine translation		 0.112017
Neural Machine Translation Leveraging Phrase-based Models in a Hybrid Search · EMNLP 2017

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

pivot translation · 0.4neural machine translation · 0.4phrase-based features · 0.3beam search · 0.3
YearPublicationVenuePosition
2019 Pivot-based Transfer Learning for Neural Machine Translation between Non-English Languages
abstract
Yunsu Kim, Petre Petrov, Pavel Petrushkov, Shahram Khadivi, Hermann Ney. 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.
Yunsu Kim 0001, Petre Petrov, Pavel Petrushkov, Shahram Khadivi, Hermann Ney
 EMNLP/IJCNLP (1)3
2017 Neural Machine Translation Leveraging Phrase-based Models in a Hybrid Search
abstract
In this paper, we introduce a hybrid search for attention-based neural machine translation (NMT).A target phrase learned with statistical MT models extends a hypothesis in the NMT beam search when the attention of the NMT model focuses on the source words translated by this phrase.Phrases added in this way are scored with the NMT model, but also with SMT features including phrase-level translation probabilities and a target language model.Experimental results on German→English news domain and English→Russian ecommerce domain translation tasks show that using phrase-based models in NMT search improves MT quality by up to 2.3% BLEU absolute as compared to a strong NMT baseline.
Leonard Dahlmann, Evgeny Matusov, Pavel Petrushkov, Shahram Khadivi
 EMNLP3