Materials of DIALOGUE 2020

10:00 - 14:00 / Section А

Different tasks of NLP (Lang:Eng/Rus)

moderated by Ekaterina Artemova

10:00 - 10:30

Elena Pimonova, Oleg Durandin, Aleksey Malafeev

Doc2Vec or Better Interpretability? A Method Study for Authorship Attribution

10:30 - 11:00

Zein Shaheen, Gerhard Wohlgenannt

Russian Natural Language Generation: Creation of a Language Modelling Dataset and Evaluation with Modern Neural Architectures

11:00 - 11:30

Valentin Malykh

Summary Construction Strategies for Headline Generation in the Russian Language

11:30 - 12:00 / Break

12:00 - 12:30

Angelina Bolshina, Natalia Loukachevitch

Generating Training Data for Word Sense Disambiguation in Russian

12:30 - 13:00

Roman Derbanosov, Maria Bakhanova

Stability of Topic Modeling via Modality Regularization

13:00 - 13:30

Tatiana Kuvshinova

Sentence compression for Russian: dataset and baselines

13:30 - 14:00

Denis Tarasov, Tatiana Matveeva, Nailya Galiullina

An Empirical Investigation of Language Model based Reverse Turing Test as a Tool for Knowledge and Skills Assessment

10:00 - 14:00 / Section В

Comparative analysis of corpuses (Lang:Rus)

moderated by Sergey Sharov

10:00 - 10:30

Sergey Sharov

Topography of Internet Corpora

10:30 - 11:00

Aleksander Piperski

Russian Language and Corpus Diversity

11:00 - 11:30

Vladimir Belikov, Vladimir Selegey, Daniil Selegey

Web-Corpus as A Tool for Linguistic Research: Differentiation, Authorization, Thematic Biases (Or Corpora We Want So Much to Believe)

11:30 - 12:00 / Panel discussion

The Present and the Future of Corpus Research

12:00 - 12:30 / Break

12:30 - 13:00

Olga Blinova, Nikita Tarasov, Valeria Modina, Ivan Belkanov

Modeling Lemma Frequency Bands for Lexical Complexity Assessment of Russian Texts

13:00 - 13:30

Julia Detkova, Valery Novitsky, Maria Petrova

Differential Semantic Sketches for Russian Internet-Corpora

13:30 - 14:00

Maksim Eremeev, Konstantin Vorontsov

Quantile-based approach to estimating cognitive text complexity

15:30 - 19:00 / Section А

Dialogue Evaluation: RuREBus-2020. NER/Relation Extraction (Lang:Eng/Rus)

moderated by Ivan Smurov

15:30 - 16:15

Vitaly Ivanin, Ekaterina Artemova, Tatiana Batura, Vladimir Ivanov, Veronika Sarkisyan, Elena Tutubalina, Ivan Smurov

RuREBus-2020 Shared Task: Russian Relation Extraction for Business

16:15 - 17:10

Vladislav Korzun

R-BERT for relationship extraction on russian business documents

Adis Davletov, Denis Gordeev, Aleksey Rey, Nikolay Arefiev

RENERSANs: Relation Extraction and Named Entity Recognition as Sequence Annotation

17:10 - 17:40 / Break

17:40 - 18:10

Denis Gordeev, Adis Davletov, Aleksey Rey

Relation extraction dataset for the Russian language

18:10 - 18:40

Mikhail Tikhomirov, Natalia Loukachevitch, Anastasiya Sirotina, Boris Dobrov

Pretraining and Augmentation in Named Entity Recognition Task for Cybersecurity Domain in Russian

18:40 - 19:10

Dmitry Evseev, Mikhail Arkhipov

SPARQL query generation for complex question answering with BERT and BiLSTM-based model

16:00 - 19:00 / Section В

Linguistic models of language (Lang: Rus)

moderated by Irina Kobozeva

16:00 - 16:30

Galina Kustova

Semantic Effects of Verb Tense in Parenthetical Constructions with Mental Verbs

16:30 - 17:00

Olga Inkova

A quantitative method for analysis of connectives: the “portrait” of the Russian conjunction ili ‘or’ in the Supracorpora database of connectives

17:00 - 17:30 / Break

17:30 - 18:00

Leonid Iomdin, Boris Iomdin

Valency structure of certain predicates of speech: new findings

18:00 - 18:30

Anton Zimmerling

Zero forms and dispersion in morphological paradigms: the verb “be” in Russian

18:30 - 19:00

Sergey Tatevosov, Ksenia Kisseleva

Semantics for OBRATNO: A Re Entry into A Discontinued State

19:30 - 21:30 / Round table

Ru_Open-Source Universe

>Our response to SuperGLUE (General Language Understanding Evaluation)

>New libraries МО ( NeoML от ABBYY)

>Tracks of DialogEvaluation 2020 (Lang: Rus)

moderated by Tatiana Shavrina