Main Page
| Line 31: | Line 31: | ||
At first glance, the UNL seems to be a multilingual machine translation system, i.e., a kind of Interlingua, to which the source texts are converted before being translated into the target languages. It can, in fact, be used for such a purpose, and very efficiently too. However, its real strength is to represent knowledge and its primary objective is to serve as an infrastructure for handling knowledge that already exists or can exist in any given language. | At first glance, the UNL seems to be a multilingual machine translation system, i.e., a kind of Interlingua, to which the source texts are converted before being translated into the target languages. It can, in fact, be used for such a purpose, and very efficiently too. However, its real strength is to represent knowledge and its primary objective is to serve as an infrastructure for handling knowledge that already exists or can exist in any given language. | ||
| − | |||
== THE UNL SOCIETY == | == THE UNL SOCIETY == | ||
Revision as of 12:58, 14 April 2009
The UNL - an acronym for “Universal Networking Language” - is a digital language that enables computers to process information and knowledge across the language barriers. It is an artificial language that replicates, in the cyberworld, the functions of natural languages in human communication. As a digital system, it makes it possible for computers to intercommunicate, thus providing people with a linguistic infrastructure for distributing, receiving and understanding multilingual information.
Contents |
THE UNL
In the UNL approach, information conveyed by natural language is represented, sentence by sentence, as a hypergraph composed of a set of directed binary labeled links (referred to as “[relations]”) between nodes or hypernodes (the “Universal Words”, or simply “UW”), which stand for concepts. UWs can also be annotated with “attributes" representing context information.
As a matter of example, the English sentence ‘The sky was blue?!’ can be represented in UNL as follows: File:Example.jpg
In the example above, "sky(icl>natural world)" and "blue(icl>color)", which represent individual concepts, are UWs; "aoj" (= attribute of an object) is a directed binary semantic relation linking the two UWs; and "@def", "@interrogative", "@past", "@exclamation" and "@entry" are attributes modifying UWs.
UWs are supposed to represent universal concepts and are expressed in English words in order to be humanly-readable. They consist of "headword" (the UW root) and a "constraint list" (the UW suffix between parentheses), the latter being used to disambiguate the general concept conveyed by the former. The set of UWs, which is currently around 63,000 entries, is organized in an ontology-like structure (the so-called "UW System"), where upper concepts are used to disambiguate the lower ones through "icl" (= is a kind of) and "iof" (= is an instance of) relations.
Relations are expected to represent semantic links between words in every existing language. They can be ontological (such as "icl" and "iof" referred to above), logical (such as "and" and "or") and thematic (such as "agt" = agent, "ins" = instrument, "tim" = time, "plc" = place, etc). There are currently 46 relations in the UNL Specs, and they define the syntax of UNL.
Attributes represent information that cannot be conveyed by UWs and relations. Normally, they represent information on tense (".@past", "@future", etc), reference ("@def", "@indef", etc), modality ("@can", "@must", etc), focus ("@topic", "@focus", etc), .and so on.
Under the UNL Program, the process of representing natural language sentences in UNL graphs is called "enconverting", and the process of generating natural language sentences out of UNL graphs is called "deconverting". The former, which involves natural language analysis and understanding, is supposed to be carried out semi-automatically (i.e., in a computer-aided human basis); the latter is expected to be done fully-automatically.
THE UNL PROGRAMME
The mission of the UNL Programme is to enable all peoples to generate, and have access to, information and knowledge in their native language and culture. The immediate goal of the Programme is to construct the UNL multilingual infrastructure in order to break down linguistic barriers that isolate and exclude a large number of people from the global community. These barriers exist because many people are not familiar with the dominant languages in which culture and knowledge are currently expressed. Its broader goal is to facilitate an interchange of cultural values among people all over the world, and in this way, to contribute to the dialogue among civilisations, to peace and to the development of all nations.
The UNL was born within the United Nations and was conceived at the Institute of the Advanced Studies of the United Nations University[1]. It is the property of the United Nations and, therefore, an asset of all of humankind. A patent application has been registered in the name of the United Nations, among the member States of the Patent Co-Operation Treaty (PCT), to ensure that it remains free for all peoples.
THE UNL SYSTEM
The UNL System consists of three main components: the linguistic resources, the software technology to manage them, and the applications that can be generated thereafter. The linguistic resources and the software technology reside in Language Servers, at least one for each language, which are inter-linked through the web. Together they form the multilingual infrastructure that enables human communication across language barriers. Furthermore, thanks to this infrastructure, it is possible to create UNL applications and services in almost all fields of human activities.
Although the UNL is an electronic language, it has all the components of a natural language. It is composed of words expressing concepts – “universal words”, also referred to as UWs - which are inter-linked with other UWs to form sentences. These links, known as “relations”, specify each single word as well as each sentence in its entirety. The specific meaning intended by the speaker can be expressed through “attributes”. A set of dictionaries and grammar rules serve as an interface between each natural language and the UNL, making it possible to obtain automatically and simultaneously the equivalent meaning in either language. In addition, the “Knowledge Base” provides a kind of semantic background to make sure the meaning of the UNL expressions is unambiguous.
At first glance, the UNL seems to be a multilingual machine translation system, i.e., a kind of Interlingua, to which the source texts are converted before being translated into the target languages. It can, in fact, be used for such a purpose, and very efficiently too. However, its real strength is to represent knowledge and its primary objective is to serve as an infrastructure for handling knowledge that already exists or can exist in any given language.
THE UNL SOCIETY
The UNL Programme is a partnership endeavour. Many institutions, R&D groups and individual researchers are interested in working on, and with, the UNL System. These are members of the UNL Society, an open-access virtual community of research created in 1999. To date, the Society has 240 members from 30 countries, with access to the tools necessary for the development of the UNL System. In January 2001, the United Nations University set up an autonomous organisation, the UNDL Foundation[2], to be responsible for the development and management of the UNL Programme. The Foundation, a non-profit international organisation, has an independent identity from the United Nations University, although it has special links with the UN. It inherited from the UNU/IAS the mandate of implementing the UNL Programme so that it can fulfil its mission. Its Headquarters are based in Geneva, Switzerland.
