Igor Boguslavsky

Igor Boguslavsky
Universidad Politécnica de Madrid | UPM · Departamento de Inteligencia Artificial

About

45
Publications
5,940
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
450
Citations

Publications

Publications (45)
Conference Paper
Full-text available
Text interpretation often requires common sense knowledge and reasoning. A convenient tool for developing methods of common sense reasoning are special sets of challenge problems whose interpretation requires sophisticated reasoning. An interesting example is a recently published data set called Triangle Choice of Plausible Alternatives (Triangle-C...
Article
Full-text available
We investigate valency properties of partials – words and constructions that express the Part/Whole relation, primarily in Russian, offering new observations largely based on the Russian National Corpus. Special attention is given to such lexical units as bol’šinstvo ‘majority’, men’šinstvo ‘minority’, čast’ ‘part’, protsent ‘percentages’, v bol’ši...
Article
Full-text available
The paper addresses a variety of expressions that quantitatively characterize an object or a situation by stating that this object or situation forms a certain part of another object or situation. Some of these expressions are polovina 'half', tret' 'a third', četvert' 'a fourth', procent 'per cent', bol'šinstvo 'majority', men'šinstvo 'minority',...
Conference Paper
Full-text available
We present a project aiming at developing a semantic analyzer based on linguistic and world knowledge. The major sources of knowledge are a semantic dictionary, an ontology, a fact base, and a set of common sense axioms. We show the types of information stored in these resources, and demonstrate how they interact. As a case study, we take a simple...
Article
Full-text available
Joint morphological and syntactic analysis has been proposed as a way of improving parsing accuracy for richly inflected languages. Starting from a transition-based model for joint part-of-speech tagging and dependency parsing, we explore different ways of integrating morphological features into the model. We also investigate the use of rule-based...
Article
Full-text available
We consider Russian coordinative constructions with paired conjunctions, such as i…i ‘both…and’, ili…ili ‘either…or’, ni…ni ‘neither…nor’, ne tol'ko…no i ‘not only…but also’, ne…a ‘not…but’, etc. The paper presents a class of syntactic constructions, so-called asymmetric constructions, which are interesting in several respects. They are closely rel...
Article
Full-text available
The paper presents a large-coverage rule-based dependency parser for Russian, ETAP-3, and results of its evaluation according to several criteria. The parser takes a morphological structure of a sentence processed as input and builds a dependency tree for this sentence using a set of syntactic rules. Each rule establishes one labeled and directed l...
Article
Full-text available
Universal Networking Language (UNL) was launched by the Institute of Advanced Studies of the United Nations University for the facilitation of multilanguage and multiethnic access to communication networks such as WWW. UNL is used to support different types of applications, from multilingual generation to abstracting and cross-lingual information r...
Conference Paper
Full-text available
The paper is devoted to the development of a system of synonymous and quasi-synonymous paraphrasing and its practical applications, first of all in the domain of search engine optimization and information extraction. This system is part of the ETAP-3 multifunctional NLP environment created by the Laboratory of Computational Linguistics of the Khark...
Conference Paper
Full-text available
We present the first results on parsing the SYNTAGRUS treebank of Russian with a data-driven dependency parser, achieving a labeled attachment score of over 82% and an unlabeled attachment score of 89%. A feature analysis shows that high parsing accuracy is crucially dependent on the use of both lexical and morphological features. We conjecture tha...
Article
Full-text available
Multilingual lexicons are needed in various applications, such as cross-lingual information retrieval, machine translation, and some others. Often, these applications suffer from the ambiguity of dictionary items, especially when an intermediate natural language is involved in the process of the dictionary construction, since this language adds its...
Conference Paper
Full-text available
In the prototypical case, arguments (=actants) are directly subordinated to their predicates and occupy positions of the subject and direct or indirect object. Valency slots filled in this way are called active. In non-prototypical cases, arguments can syntactically subordinate their predicate (passive valency slots) and even have no immediate synt...
Conference Paper
UNL is an enterprise to support multilinguality in Internet based on a common language calledUniversal Networking Language. One of the components of the language is a dictionary of Universal Words(UWs). Such dictionary constitutes the link between the vocabularies of the languages involved in the Project.This article describes the process of creati...
Conference Paper
Full-text available
In a recent experiment on translating a web site into 4 languages, we have confirmed that using MT results in "translator's mode" can reduce the human work to produce good translations of complex sentences (25 w) at a rate of 25 mn/p with all-purpose commercial MT and at 20 mn/p with lab quality MT. A subexperiment has shown that using deconversion...
Conference Paper
This paper describes a new method to produce massive multilingual dictionaries to support other applications, like multilingual search engines, multilingual chats, mobile applications and others. The classical approach to build multilingual dictionaries frequently pivots around the English language. Another approach requires the existence of biling...
Article
Full-text available
We describe a project aimed at creating a deeply annotated corpus of Russian texts. The annotation consists of comprehensive morphological marking, syntactic tagging in the form of a complete dependency tree, and semantic tagging within a restricted semantic dictionary. Syntactic tagging is using about 80 dependency relations. The syntactically ann...
Conference Paper
Full-text available
The paper presents the module of interactive word sense disambigua- tion and syntactic ambiguity resolution used within a machine translation sys- tem, ETAP-3. The method applied consists in asking the user to identify a word sense, or a syntactic interpretation, whenever the system lacks reliable data to make the choice automatically. In lexical d...
Conference Paper
Full-text available
We are presenting a description of the UNL initiative based on the Universal Networking Language (UNL). This language was conceived to be the support of the multilingual communication on the Internet beyond the linguistic barriers. This initiative was launched by the Institute of Advanced Studies of the United Nations University in 1996. The initia...
Article
Full-text available
The paper presents the work done at the Institute for Information Transmission Problems (Russian Academy of Sciences, Moscow) on the multifunctional linguistic processor ETAP-3. Its two multilingual options are discussed – machine translation in a variety of language pairs and translation to and from UNL, a meaning representation language. For each...
Conference Paper
Full-text available
The paper presents the work done at the Institute for Information Transmission Problems (Russian Academy of Sciences, Moscow) on the multifunctional linguistic processor ETAP-3. Its two multilingual options are discussed -- machine translation in a variety of language pairs and translation to and from UNL, a meaning representation language. For eac...
Article
Full-text available
The papel' describes a tagging scheme dcsigucd for the P, ussian Treebank, and presents tools used for corpus creation.
Article
Full-text available
Résumé Les mots à positions de valence sémantique passives et discontinues ont des propriétés radicalement différentes des mots à valence habituels. Ces types de positions de valence ne sont pas remplis par des actants syntaxiques et ne peuvent par conséquent être décrits par des schémas de gouvernement. Un mot qui occupe une telle position n'est p...
Article
Full-text available
Résumé Cet article décrit l'utilisation du concept de fonctions lexicales, tel que proposé par la "théorie sens-texte" (TST) d'Igor Mel'čuk, dans des applications avancées de TAL telles que les analyseurs, la traduction automatique (TA) de bonne qualité, les systèmes de paraphrase et l'apprentissage du lexique assisté par ordinateur, applications i...
Article
Full-text available
A module for enconversion of NL texts into Universal networking Language (UNL) graphs is considered. This module is designed for the system of multi- lingual communication in the Internet that is being developed by research centers of about 15 countries under the aegis of UN. The enconversion of NL texts into UNL is carried out by means of a multi-...
Article
Full-text available
The paper describes a tagging scheme designed for the Russian Treebank and presents tools used for corpus creation. 1. Introductory Remarks The present paper describes a project aimed at developing the first annotated corpus of Russian texts. Large text corpora have been used in the computational linguistics community for quite a long time now; at...
Article
Full-text available
The Universal Networking Language (UNL) developed by Dr. H. Uchida at the Institute for Advanced Studies of the United Nations University is a meaning representation language designed for multilingual communication in electronic networks, information retrieval, summarization and other applications. We discuss several features of this language relev...
Article
Full-text available
A multifunctional NLP environment, ETAP-3, is presented. The environment has several NLP applications, including a machine translation system, a natural language interface to SQL type databases, synonymous paraphrasing of sentences, syntactic error correction module, and a computer-assisted language learning tool. Emphasis is laid on a new module o...
Conference Paper
Full-text available
File paper describes a tagging scheme designed for the Russian Treebank, and presents tools used for corpus creation. 1. lntrodudory Remarks The present paper describes a project aimed at developing the first annotated corpus of P, ussian texts. I.arge text coq~ora trove been used in the computational linguistics community long enough: at present,...
Article
Full-text available
The article presents a dictionary of concepts, developed as a part of the ongoing effort to create an intermediary language for global information exchange based on semantic structures. The article describes basic principles and contents of the dictionary, which has a potential to become a publicly available language-neutral resource.
Article
Full-text available
We discuss several linguistic aspects of the Universal Networking Language (UNL); in particular, those connected with Universal Words (UWs), UNL relations, and hypernodes. On the one hand, the language should be rich enough and provide sufficient means to express the knowledge that might be required in the applications it is intended for. On the ot...
Article
Full-text available
Abstract The paper describes the use of lexical functions, an instrument proposed in Igor Melčuk's Meaning ⇔ Text linguistic model, in advanced NLP applications, including parsers, high quality machine translation, a system of paraphrasing and computer-aided learning of lexica. In parsing, collocate LFs are used to resolve ,or reduce ,syntactic and...
Article
Full-text available
A multifunctional NLP environment, ETAP-3 linguistic processor, is presented. The environment, largely based on the Meaning Text Theory, offers several NLP applications, including a machine translation system, a module of synonymous paraphrasing of sentences, a tagger for syntactic annotation of text corpora, a Universal Networking Language interfa...
Article
Full-text available
We describe a recently launched project whose objective is to develop an advanced converter of natural language text to semantic structures. The project basically consists in enriching the ETAP-3 linguistic processor, developed by the Institute for Information Transmission Problems, Russian Academy of Sciences, with a new module – that of semantic...
Article
Full-text available
1 The paper discusses the semantics of Russian comparatives with the attenuative prefix po-like pobol'še 'somewhat more' or poumnee 'a bit cleverer'. It is shown that they have two major types of usage, the comparative one and the selective one. The former is close to the semantics of the standard comparative degree of adjectives and adverbs, while...
Article
Full-text available
A universal dictionary of concepts, developed as a part of the ongoing effort to create a semantic intermediary language for global information exchange, is presented. The article describes basic principles and contents of the dictionary and outlines the current state of the project. The dictionary can evolve into an open and freely available langu...

Network

Cited By

Projects

Project (1)