Lab 15

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.

On présente la description du processeur linguistique ETAP-3, qui constitue un environnement multifonctionnel pour le traitement du langage naturel. Cet environnement, essentiellement basé sur la théorie Sens Û Texte, offre plusieurs applications pratiques, dont un système de traduction automatique, un système de paraphrase synonymique, un système d'annotation syntaxiques d'un corpus de textes, un interface UNL, un système d'enseignement des langues étrangères assisté par ordinateur, un interface permettant de dialoguer en langage naturel avec les bases de données de type SQL et un système de correction automatique des erreurs syntaxiques dans le texte. L'article, qui contient un bref aperçu de toutes les applications mentionnées, porte un accent particulier sur la traduction automatique qui est de loin l'application la plus développée de cet environnement.

 A module for enconversion of NL texts into Universal networking Language (UNL) graphs is considered. This module is designed for the system of multilingual 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-functional linguistic processor ETAP-3, developed in the Computational linguistics laboratory of the Institute for Information Transmission Problems of the Russian Academy of Sciences. One of the major problems in the automatic text analysis is high degree of ambiguity of linguistic units. The resolution of this ambiguity (morphological, syntactic, lexical, translational) is partly ensured by the linguistic knowledge base of ETAP-3, but complete algorithmic solution of this problem is unfeasible. We describe an interactive system that helps resolve difficult cases of linguistic ambiguity by means of a dialogue with the human. Index Terms  interactive disambiguation, knowledge representation, UNL system, parsing. © Convergences ´03 December 2 -6, 2003, Alexandria, EGYPT International Conference on the Convergence of Knowledge, Culture, Language and Information Technologies 2 explicitly referred to in the dictionary entries of the words making up the sentence.

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 annotated corpus counts more than 28,000 sentences and makes an autonomous part of the Russian National Corpus (www.ruscorpora.ru). Semantic tagging is based on an inventory of semantic features (descriptors) and a dictionary comprising about 3,000 entries, with a set of tags assigned to each lexeme and its argument slots. The set of descriptors assigned to words has been designed in such a way as to construct a linguistically relevant classification for the whole Russian vocabulary. This classification serves for discovering laws according to which the elements of various lexical and semantic classes interact in the texts. The inventory of semantic descriptors consists of two parts, object descriptors (about 90 items in total) and predicate descriptors (about a hundred). A set of semantic roles is thoroughly elaborated and contains about 50 roles.

Empirical Weights in Parsing. The paper discusses a complex of solutions aimed at ambiguity resolution in the parsing component of a multipurpose NLP system, ETAP-3. The main idea is to introduce a system of priorities, or weights, dynamically produced for the elements of the text processed and of the structure generated during all parsing phases. These weights, empirically assigned to lexical entries and fragments of parsing rules, help tune the parser to the generation of an optimal syntactic structure of an ambiguous sentence.

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 annotated corpus counts more than 28,000 sentences and makes an autonomous part of the Russian National Corpus (www.ruscorpora.ru). Semantic tagging is based on an inventory of semantic features (descriptors) and a dictionary comprising about 3,000 entries, with a set of tags assigned to each lexeme and its argument slots. The set of descriptors assigned to words has been designed in such a way as to construct a linguistically relevant classification for the whole Russian vocabulary. This classification serves for discovering laws according to which the elements of various lexical and semantic classes interact in the texts. The inventory of semantic descriptors consists of two parts, object descriptors (about 90 items in total) and predicate descriptors (about a hundred). A set of semantic roles is thoroughly elaborated and contains about 50 roles.

The paper describes the incorporation of statistical knowledge into two different Rule-Based MT (RBMT) systems. In earlier experiments, these systems were linked with Memory-Base MT components, so that by now the translation process is supported by three MT paradigms. ...

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 the latter is closer to the semantics of the superlative. Within the comparative type a special case is described: the correlative construction which contains two attenuatives. Its outstanding feature is cross-filling of valency slots of the comparatives.

Résumé Le présent article traite d’un ensemble de solutions visant la résolution des ambiguïtés dans la composante syntaxique du système polyvalent de traitement automatique de la langue, ETAP-3. L’idée principale est d’introduire un système de poids, ou de priorités, dynamiquement produits pour les éléments du texte traité et pour les structures générées en cours d’analyse syntaxique. Ces poids, empiriquement assignés aux descriptions des unités lexicales et aux règles d’analyse, permettent à l’analyseur syntaxique de trouver la procédure d’analyse optimale pour une phrase ambiguë.

Résumé On présente ETAP-2, un système de traduction automatique (anglais-russe), en insistant sur ce qui le différencie des autres systèmes du point de vue linguistique. On expose ensuite quelques échantillons de traductions réalisées avec ETAP-2 puis on évalue la qualité des résultats et la vitesse…

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 working language, ETAP has one integral dictionary, which is used in all applications both for the analysis and synthesis (generation) of the given language. In difficult cases, interactive dialogue with the user is used for disambiguation. Emphasis is laid on multiple use of lexical resources in the multilingual environment. 1 General Information on ETAP The multifunctional ETAP-3 linguistic processor, developed by the Computational Linguistic s Laboratory (CLL) in Moscow (see e.g. Apresjan et al. 1992a,b, 1993, 2003), is the product of more than two decades of laboratory research and development in the field of language modeling. The mo...

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 that the latter result can be generalized to richly inflected languages in general, provided that sufficient amounts of training data are 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 interface, a computer-assisted language learning tool, a natural language interface to SQL type databases,

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 working language, ETAP has one integral dictionary, which is used in all applications both for the analysis and synthesis (generation) of the given language. In difficult cases, interactive dialogue with the user is used for disambiguation. Emphasis is laid on multiple use of lexical resources in the multilingual environment.