Nikita Mediankin


2019

pdf bib
ÚFAL-Oslo at MRP 2019: Garage Sale Semantic Parsing
Kira Droganova | Andrey Kutuzov | Nikita Mediankin | Daniel Zeman
Proceedings of the Shared Task on Cross-Framework Meaning Representation Parsing at the 2019 Conference on Natural Language Learning

This paper describes the ÚFAL--Oslo system submission to the shared task on Cross-Framework Meaning Representation Parsing (MRP, Oepen et al. 2019). The submission is based on several third-party parsers. Within the official shared task results, the submission ranked 11th out of 13 participating systems.

2018

pdf bib
SumeCzech: Large Czech News-Based Summarization Dataset
Milan Straka | Nikita Mediankin | Tom Kocmi | Zdeněk Žabokrtský | Vojtěch Hudeček | Jan Hajič
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)

2016

pdf bib
ConFarm: Extracting Surface Representations of Verb and Noun Constructions from Dependency Annotated Corpora of Russian
Nikita Mediankin
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: System Demonstrations

ConFarm is a web service dedicated to extraction of surface representations of verb and noun constructions from dependency annotated corpora of Russian texts. Currently, the extraction of constructions with a specific lemma from SynTagRus and Russian National Corpus is available. The system provides flexible interface that allows users to fine-tune the output. Extracted constructions are grouped by their contents to allow for compact representation, and the groups are visualised as a graph in order to help navigating the extraction results. ConFarm differs from similar existing tools for Russian language in that it offers full constructions, as opposed to extracting separate dependents of search word or working with collocations, and allows users to discover unexpected constructions as opposed to searching for examples of a user-defined construction.