Corpus ID: 9877683

Building a Dependency Parsing Model for Russian with MaltParser and MyStem Tagset

  title={Building a Dependency Parsing Model for Russian with MaltParser and MyStem Tagset},
  author={Kira Droganova},
The paper describes a series of experiments on building a dependency parsing model using MaltParser, the SynTagRus treebank of Russian, and the morphological tagger Mystem. The experiments have two purposes. The first one is to train a model with a reasonable balance of quality and parsing time. The second one is to produce user-friendly software which would be practical for obtaining quick results without any technical knowledge (programming languages, linguistic tools, etc.). 

Figures from this paper

Building NLP Pipeline for Russian with a Handful of Linguistic Knowledge
This work addresses the issue of building a free NLP pipeline for processing Russian texts all the way from plain text to morphologically and syntactically annotated conll. The pipeline is written inExpand
Learning syntactic tagging of Macedonian language
Four well-known PoS tagger systems implemented for English and Slavic languages: TnT, cyclic dependency network, guided learning framework for bidirectional sequence classification, and dynamic features induction were trained and a POS tagger with an accuracy that reaches 97.5% was achieved. Expand
NLP PiPeLiNe for russiaN: aN easy-to-use Web aPPLicatioN for MorPhoLogicaL aNd syNtactic aNNotatioN
The aim of this paper is to present an easy-to-use web application specifically developed for annotating Russian texts with morphological and syntactic information. The application is built upon theExpand
Syntactic Model for Russian: Deep Learning Models with Dependency Parsing Scheme
A set of modular neural network topologies based on composition of Stack long short-term memory layers, multilayer perceptron has been compared with widely used algorithms of classification on base of Gradient boosting trees and Support vector machine. Expand
Ещё раз о способах снятия структурной омонимии: выбор единственной структуры в парсере Hurma
Целью проекта Хурма является создание исследовательской платформы для анализа текстов на естественном языке, в первую очередь на русском. Данная платформа предполагает анализ текстов на различныхExpand


Parsing the SynTagRus Treebank of Russian
The first results on parsing the SynTagRus treebank of Russian with a data-driven dependency parser are presented, achieving a labeled attachment score of over 82% and an unlabeled attachment score, conjecture that the latter result can be generalized to richly inflected languages in general. Expand
MaltParser: A Language-Independent System for Data-Driven Dependency Parsing
Experimental evaluation confirms that MaltParser can achieve robust, efficient and accurate parsing for a wide range of languages without language-specific enhancements and with rather limited amounts of training data. Expand
The proper place of men and machines in language technology Processing Russian without any linguistic knowledge
The paper describes several experiments aimed at designing tools for processing Russian texts, namely for Part-Of-Speech tagging, lemmatisation and syntactic parsing, exploiting exclusivelyExpand
A Fast Morphological Algorithm with Unknown Word Guessing Induced by a Dictionary for a Web Search Engine
A simple yet practical algorithm of morphological analysis and synthesis that uses a limited dictionary to obtain morphology of a wide lexical coverage is described, implemented for Russian, Polish and English. Expand
User Guide for MaltEval
  • (beta),
  • 2014
ETAP parser : state of the art . In Computational linguistics and intellectual technologies
  • Proceedings of International Workshop Dialogue 2012 . Vol . 11 ( 18 ) , 2012
  • 2012
ETAP parser: state of the art
  • Proceedings of International Workshop Dialogue 2012. Vol
  • 2012
Ocenka metodov avtomaticheskogo analuza teksta 2011-2012: Sintaksicheskie parsery russkogo jazyka [NLP evaluation 2011-2012: Russian syntactic parsers
  • In Computational linguistics and intellectual technologies. Proceedings of International Workshop Dialogue 2012. Vol
  • 2012