Skip to content
Free planNo credit card requiredStart writing
AI for Research home
AI for Research home
Dashboard
Sign inGet started

Search 250 million research papers

Read the abstract, see who wrote it and who cites it, and get the citation in APA, MLA, Chicago or Harvard.

About 232 papers for “Universal Networking Language”

Translation Challenges and Universal Networking Language

Baljeet Kaur, D. K. Veer · International Journal of Computer Applications · 2016

This paper presents challenges being faced in designing automatic translation software. There are many approaches to automatic translation like Direct, Rule based, Transfer based, Statistical based and Interlingua. A brief description of all the approaches and their advantages and drawbacks are discussed. Universal Networking Language (UNL) based on Interlingua approach can be used especially for translation among multiple languages because it requires knowledge of UNL and of the language which user wants UNL to support. User can then get translated text in any of the languages supported by UNL without even being oblivious to any other language. It is less expensive approach also. This paper also gives brief introduction to UNL and how it can overcome many of the challenges in translation.

Cited by 3Open access

El sistema UNL, Universal Networking Language

Cardeñosa Lera, Jesús, Tovar Caro, Edmundo, Gallardo Pérez, Carolina · LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas) · 2002

Se describe a continuación un breve resumen del Sistema UNL, proyecto financiado\n\t\t\t\t por el Instituto de Estudios Avanzados de la Universidad de las Naciones Unidas, donde se\n\t\t\t\t explicarán los principales objetivos del proyecto, la evolución que ha tenido y los resultados\n\t\t\t\t obtenidos hasta ahora.

Cited by 0Open access

Semantic Similarity Assessment using Universal Networking Language

A. Chitra, Anupriya Rajkumar · 2021

Semantic similarity assessment is a key problem in Natural Language Understanding which finds wide application in Information Retrieval and Extraction. Determining whether two natural language text units are semantically equivalent is a challenging task. In this work, a machine learning approach bas

Cited by 1Open access

Amazigh verb in the Universal Networking Language

Imane Taghablout, Fadoua Ataa Allah, Mohamed El Marraki · 2015

In the perspective of achieving an UNL (Universal Networking Language) based machine translation system for Amazigh language, we are undertaking the first steps of dictionaries' development according to the UNL specifications. So far, no attempt has been made to integrate Amazigh language in the UNL project. This latter revolves around the development of an EnConverter (Analyzer) and a DeConverter (Generator) for a natural language in order to overcome language barriers and promote multilingualism. This paper focuses on morphological analysis and semantic information of Amazigh verbs, with the aim to incorporate them into the Amazigh UNL dictionary.

Cited by 2

Constructing Better Document Vectors Universal Networking Language (UNL)

Chirag Shah, Bhoopesh Chowdhary, Pushpak Bhattacharyya · 2002

Encoding a document in a vector is a very crucial step for any vector space model based IR (Information Retrieval) system. It is obvious that the better these vectors are constructed, the better the performance of any application built on top of it. In traditional document representation methods, a document is considered as a bag of words. The fact that the words may be semantically related- a crucial information for document representation- is not taken into account. The feature vector representing the document is constructed from the frequency count of document terms. In this paper we describe a new method for generating feature vectors, using the semantic relations between the words in a sentence. The semantic relations are captured by the Universal Networking Language (UNL) which is a recently proposed semantic representation for sentences. In order to show that the generated document vectors with this new method are better than the traditional methods, we use the concept of mutual information. We prove by experiments that the vectors generated by UNL method indeed provide more information about the documents. It is proved that this helps in improving precision-recall in an IR system built using them.

Cited by 0

Outlining Bangla Word Dictionary for Universal Networking Language

Mohammad Zakir Hossain Sarker · IOSR Journal of Computer Engineering · 2012

Universal Networking Language (UNL) is a computer language that enables computers to process information and knowledge across the language barriers. It is an artificial language that replicates the functions of natural languages in human communication. The main goal of the UNL system, which allows users to visualize websites in their native languages, is to provide a common representation for accessing Internet of multilingual. For this common representation, lexical knowledge is a critical issue in natural language processing systems. We have been working to include Bangla in the UNL system and in this paper we have discussed about the Bangla Word Dictionary that we have designed to include in the system.

Cited by 3Open access

Universal Networking Language (UNL) som interlingua for maskinoversettelse

John B. Lervik · Duo Research Archive (University of Oslo) · 2004

Nøkkelord: Maskinoversettelse, automatisk oversettelse, interlingua, representasjon av mening, formell semantikk, UNL, UNLP, UNDL.\n\nUniversal Networking Language (UNL) er et elektronisk interlingua (mellomspråk) med et demokratisk siktemål, ved at det skal fungere som et mellomledd via internett mellom forskjellige språk i verden, slik at mennesker på sitt eget morsmål skal få del i informasjon og kunnskap. Programmet for utvikling og vedlikehold av systemet er initiert av FN og videreføres av The Universal Networking Digital Language Foundation (UNDL) i Geneve. De språkspesifikke modulene utvikles av lokale språksentre. Mulige bruksområder er maskinoversettelse (automatisk oversettelse), virtuell kommunikasjon, fjernundervisning, informasjonsgjenfinning og søkemotorer, ekspertsystemer.\n\nHovedoppgaven er tredelt: UNLs bakgrunn, syntaks og semantikk; tre andre formalismer (Første ordens logikk, Montague-semantikk, Event-semantikk); sammenlikning av UNL med de andre formalismene, med konklusjoner.\n\nKonklusjon: UNL er bedre egnet for maskinoversettelse enn de andre formalismene. I mange tilfeller oppnås tilstrekkelig gode oversettelser med UNL, og uttrykkskraften er større. Systemet fungerer foreløpig kun for oversettelse fra UNL til enkelte naturlige språk, best til spansk, russisk og til dels italiensk. Hvor egnet UNL er for formålet kan ikke vurderes før det blir mulig å oversette motsatt vei. Dessuten må språkservere utvikles for atskillig flere skriftspråk. Infrastruktur for bruk av internett må tilrettelegges og datamaskiner må gjøres tilgjengelig for almennheten, i global forstand. Det største problemet vil nok ikke være de lingvistiske utfordringene, men om tilstrekkelig mange land kan og vil bruke de enorme ressursene som kreves for en slik utvikling, både når det gjelder ledelse, økonomi og teknikk.\n\nNyttig bakgrunnsstoff:\nDorr, Bonnie J., Pamela W. Jordan og John W. Benoit (1999): A Survey of Current Paradigms in Machine Translation, Advances in Computers, Vol 49, M. Zelkowitz (Ed), Academic Press, London, pp. 1-68 http://www.umiacs.umd.edu/~bonnie/publications.html\nNirenburg, Sergei, Harold L. Somers og Yorick Wilks (red.) (2003): Readings in Machine Translation, MIT Press, Cambridge, Massachusetts (snart tilgjengelig)\nUNDL (2003): UNDL Foundation, Internett 16.10.2003 http://www.undl.org/

Cited by 0Open access

Towards a Universal Language for Distributed Intelligent Robot Networking

Masao Yokota · 2006

M. Yokota et al have proposed a formal language L <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">md</sub> for facilitating the distributed intelligent robot network (DIRN) consisting of one brain node and numerous sensor and actor nodes with human-friendly interfaces. In order to realize well-coordinated DIRNs, it is very important to develop a systematically computable knowledge representation language universal for any kind of device as well as efficient networking technologies. As a candidate for this purpose, the L <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">md</sub> was evaluated by applying it to integrated multimedia understanding and various cross-media operations in simulation of DIRN-world interaction.

Cited by 8

Morphological analysis of Kokborok for universal networking language dictionary

Khumbar Debbarma, Braja Gopal Patra, Swapan Debbarma et al. · 2012

This paper focuses on morphological analysis of Kokborok words to incorporate them into Kokborok dictionary and Kokborok Machine translator. So far, no attempt has been made to integrate the works for a concrete computational output. In this paper we particularly emphasize on bringing works on morphological analysis in the frame, with the goal to produce a Kokborok-dictionary, as well as Machine Translator, which will provide a unified base to fit into already developed universal conversion systems of UNL. We explain the morphological rules of Kokborok words for UNL structures. These rules tend to expose the modifications of parts of speech with regards to tense, person, subject etc. of the words of a sentence. Here we outline the morphology of nouns, verbs and adjective phrases only.

Cited by 7

Conversion of Bangla Sentence into Universal Networking Language Expression

Nawab Yousuf Ali, Mohammad Zakir, Hossain Sarker et al. · 2011

Conversion from another language to native language is highly demanding due to increasing the usage of web based application. Firstly, the respective sentence of a native language is converted to Universal Networking Language (UNL) expressions and then UNL expressions can be converted to any native language. UNL system is developed for most of the languages already but a very little effort has been made to convert Bangla language to UNL expressions. In this paper we have described our work to convert Bangla Sentence into UNL Expression. To do this we have described UNL, Bangla grammar, the rules that we have designed for converting Bangla sentence into UNL expression. Finally, we have applied our rules in a Bangla sentence and demonstrated the conversion.

Cited by 7

Algorithm for Conversion of Bangla Sentence to Universal Networking Language

Md. Nawab Yousuf Ali, Mortuza Ali, Abu Mohammad Nurannabi et al. · 2010

Conversion from another language to native language is highly demanding due to increasing the usage of web based application. Firstly, the respective sentence of a native language is converted to Universal Networking Language (UNL) expressions and then UNL expressions can be converted to any native language. Already UNL system is developed for most of the languages, but there are no algorithms to convert Bangla sentence to UNL expressions. This paper presents newly developed algorithms for conversion of Bangla sentence into UNL expressions. Theoretically it proves its ability to convert from Bangla sentence to UNL expression.

Cited by 3

A statistical approach for universal networking language-based relation extraction

Dat Nguyen, Mitsuru Ishizuka · 2006

In the effort to enrich available information with machine-processable semantics, Universal Networking Language (UNL) was defined as an artificial intelligent language that is able to represent information and knowledge described in natural languages. One of the main components of UNL is a set of binary relations that represents semantic relationships between concepts in sentences. To provide machine-processable semantics for computers, extraction of such semantic relationships from natural language text is a must. In this paper, we present a method to solve the problem of UNL semantic relation extraction in English sentences. With the assumption that the positions of phrases in a sentence between which there exists a relation have been identified, we focus on the problem of classifying the relation between the given phrases. The UNL relation classifier was developed by using statistical techniques applied on several lexical and syntactic features. In addition to the common used features, we also propose a new feature that reflects the actual semantic relation of two phrases independent on words in the between. Using our new feature in this problem gives the preliminary results that have shown the promising advantages of the feature in some other semantic relation recognition tasks. The evaluation on dataset supplied by UNDL organization shows that our system obtained the result at about 79% accuracy.

Cited by 6

Creating a Universal Networking Language module within an advanced NLP system

Igor Boguslavsky, Nadezhda Frid, Leonid Iomdin et al. · 2000

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 of the processor responsible for the interface with the Universal Networking Language, a recent product by the UN University intended for the facilitation of multilanguage, multiethnic access to communication networks such as WWW. The UNL module of ETAP-3 naturally combines the two major approaches accepted in machine translation: the transfer-based approach and the interlingua approach.

Cited by 25Open access

Dictionary Entries for Bangla Consonant Ended Roots in Universal Networking Language

Mohammad Zakir Hossain Sarker, Md. Nawab Yousuf Ali, Jugal Krishna Das · 2016

The Universal Networking Language (UNL) deals with the communication across nations of different languages and involves with many different related discipline such as linguistics, epistemology, computer science etc. It helps to overcome the language barrier among people of different nations to solve problems emerging from current globalization trends and geopolitical interdependence. We are working to include Bangla language in the UNL system so that Bangla language can be converted to UNL expressions. As a part of this process currently we are working on Bangla Consonant Ended Verb Roots and trying to develop lexical or dictionary entries for the Consonant Ended Verb Roots. In this paper, we have presented our work by describing Bangla verb, Verb root, Verbal Inflections and then finally showed the dictionary entries for the consonant ended roots.

Cited by 0