P
Pavel Braslavski
Researcher at Ural Federal University
Publications - 64
Citations - 536
Pavel Braslavski is an academic researcher from Ural Federal University. The author has contributed to research in topics: Question answering & Computer science. The author has an hindex of 11, co-authored 58 publications receiving 363 citations. Previous affiliations of Pavel Braslavski include Yandex & National Research University – Higher School of Economics.
Papers
More filters
Proceedings ArticleDOI
What Do You Mean Exactly?: Analyzing Clarification Questions in CQA
TL;DR: The dialogues between the users on a community question answering (CQA) website is explored as a rich repository of information-seeking interactions and the problem of predicting the specific subject of a clarification question is explored, a first step towards automatic generation of clarification questions.
Proceedings Article
Towards a Reference Corpus of Web Genres for the Evaluation of Genre Identification Systems
Georg Rehm,Marina Santini,Alexander Mehler,Pavel Braslavski,Rüdiger Gleim,Andrea Stubbe,Svetlana Symonenko,Mirko Luigi Aurelio Tavosanis,Vedrana Vidulin +8 more
TL;DR: An international and multi-disciplinary research collaboration aims at the construction of a reference corpus of web genres to contain multi-level tags of the respective genre or genres a web document or a website instantiates.
Proceedings ArticleDOI
Large Dataset and Language Model Fun-Tuning for Humor Recognition
TL;DR: A dataset of jokes and funny dialogues in Russian from various online resources is collected and complemented them carefully with unfunny texts with similar lexical properties to prove the reliability of the corpus construction approach.
Proceedings ArticleDOI
A Spinning Wheel for YARN: User Interface for a Crowdsourced Thesaurus
TL;DR: YARN (Yet Another RussNet) project as discussed by the authors aims at creating a large open thesaurus for Russian using crowdsourcing and describes synset assembly interface developed within the project.
Book ChapterDOI
SberQuAD -- Russian Reading Comprehension Dataset: Description and Analysis.
TL;DR: SberQuAD -- a large scale analog of Stanford SQuAD in the Russian language - is a valuable resource that has not been properly presented to the scientific community by providing a description, a thorough analysis, and baseline experimental results.