Interactive Enconversion by Means of the ETAP-3 System

2000

This paper presents an interlingua approach to the machine translation of lengthy documents. This appr oach is based on encoding the source text in the form of universa l semantic networks, using the Universal Networking Language, UNL interlingua, which can then be decoded back into any natural language. This UNL technology has been applied to 1000 pages from the Encyclopedia

… Corpora: encoding, structuring, analysis. 11th Annual …, 1999

Web 3.0 (Semantic Web) is considered a leap forward in people’s interaction with the web. It is based on refining the search and creating multimedia reports that contain relevant information gathered from multiple sources. Still, this attempt also includes the need for a common language and software able not only to extract and unite data, but also to translate the information and make it available to a larger public.

Universal Networking Language (UNL), Universal Word (UW), converter/deconverter, multilingual translation, linguistic alignment and correspondences of documents, parallel multilingual documents Summary The paper aims to present multilingual document alignment and translation on the platform OGA (Outil de Gestion d'Alignement, Alignment Gestion Tool) by using the UNL (Universal Networking Language). Essential management allowed by OGA is to create a parallel multilingual document by importing in the associated data base the different monolingual files, edited on different software, corresponding to its resources in several languages. UNL is a sort of interlingua such as pivot languages in certain MT systems, which enables to translate documents into several different languages. UNL system contains UW dictionaries, decorder and encorder. The typical sitution OGA engages in is the internationalization of same documents in different languages in small office, that's the situation where documents alignment and translation are required at the same time. OGA was developed to fulfill these needs in a user-friendly environment. We describe, first, OGA and UNL language. Second, we introduce UNL expressions rewritten from French leaflet by screen images on OGA. Third, we make a French generation experimentation by using a deconverter. Finally, we discuss the adventage of UNL language and its application to the translation on OGA, while comparing OGA with other software.

NAACL-ANLP 2000 Workshop on Applied interlinguas practical applications of interlingual approaches to NLP -, 2000

In this paper, we describe the Universal Networking Language, an interlingua to be plugged in a Web environment aiming at allowing for many-to-many information exchange, 'many' here referring to many natural languages. The interlingua is embedded in a Knowledge-Base MT system whose languagedependent modules comprise an encoder, a decoder, and linguistic resources that have been developed by native speakers of each language involved in the project. Issues concerning both the interlingua formalism and its foundational issues are discussed.

2008

We describe a system for converting English sentences into expressions of an interlingua called Universal Networking Language (UNL). UNL represents knowledge in form of semantic network, where nodes represent concepts and links represent semantic roles between concepts. UNL nodes also contain semantic attributes like number, tense, aspect, mood, negation etc. Our system uses a lexicalized probabilistic parser to get the typed dependency tree and the phrase structure tree for a given English sentence. The system then converts dependency relations into UNL relations and attributes based on the POS tags of the words involved in the relation, and their semantic attributes obtained from the Princeton Wordnet. UNL hypernodes called scopes are generated by considering the relative positions of the words in the phrase structure tree. Correct handling of UNL scopes is a distinctive aspect of our work. We are not aware of any other enconversion system that attempts generating scopes, which ar...

2015

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

TJPRC, 2013

The UNL is a computer language that allows computers to process information and knowledge. It is an artificial language that replicates the functions of natural languages. Using the UNL, people can express all kinds of information and knowledge that expressed by natural languages and computers can intercommunicate using such information and knowledge. A good number of researchers in computational linguistic all over the world have already started developing UNL system for their respective native language. In our previous research papers we also develop some rules for convert bangle sentence to UNL expression. But here we try to demonstrate a model which can implement database with the help of universal networking language. Very few researcher of the world worked about this issue. But so far no immense attempt has been made for implement database through universal networking language. In this paper we particularly emphasizing of make a model which can convert an UNL expression to database by the help of previous work that includes English –UNL dictionary, DBMS software, Bangla natural language sentences to UNL expressions converter, regular expression and vice versa.

2003

This paper aims at presenting and describing HERMETO, a computational environment for fullyautomatic, both syntactic and semantic, natural language analysis. HERMETO converts a list structure into a network structure, and can be used to enconvert from any natural language into the Universal Networking Language (UNL). As a language-independent platform, HERMETO should be parameterized for each language, in a way very close to the one required by the UNL Center's EnConverter. However, HERMETO brings together three special distinctive features: 1) it takes rather high-level syntactic and semantic grammars; 2) its dictionaries support attribute-value pair assignments; and 3) its user-friendly interface comprises debug, compiling and editing facilities. In this sense, HERMETO is said to provide a better environment for the automatic production of UNL expressions.

2004

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.