Introduction to UNL

The Universal Networking Language (UNL) is a knowledge representation language that has been used in several different fields of natural language processing, such as machine translation, multilingual document generation, summarization, information retrieval and extraction, sentiment analysis and semantic reasoning.

History

The UNL Programme started in 1996, as an initiative of the Institute of Advanced Studies of the United Nations University in Tokyo, Japan. In January 2001, the United Nations University set up an autonomous organization, the UNDL Foundation, 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. Its headquarters are based in Geneva, Switzerland.

The UNL Programme has already crossed important milestones. The overall architecture of the UNL System has been developed with a set of basic software and tools necessary for its functioning. These are being tested and improved. A vast amount of linguistic resources from the various native languages already under development has been accumulated in the last few years. Moreover, the technical infrastructure for expanding these resources is already in place, thus facilitating the participation of many more languages in the UNL system from now on. A growing number of scientific papers and academic dissertations on the UNL are being published every year.

The most visible accomplishment so far is the recognition by the Patent Co-operation Treaty (PCT) of the innovative character and industrial applicability of the UNL, which was obtained in May 2002 through the World Intellectual Property Organisation (WIPO). Acquiring the patent for the UNL is a completely novel achievement within the United Nations.

Commitments

The main goal of the UNL Programme is to construct the UNL, an artificial language that could be used to process information across the language barriers. The major commitments of the UNL are the following:

I - The UNL must represent knowledge

The UNL is an artificial language designed to represent knowledge. In this sense, the UNL is first and foremost a knowledge representation language. The most important corollary of this first commitment is that UNL is not intended to describe or represent natural languages. It is used to describe and represent the information conveyed by natural languages. The goal of UNL is to represent "what is known" and not "what was said" or "how it was said". Accordingly, the UNL is not committed to preserve the lexical and the structural choices of the original, but must represent, in a non-ambiguous format, one of its possible meanings, preferably the most conventional one. For instance, given the sentence "The present King of France is bald.", the UNL representation should state that there are entities such as kings and France, that there are properties such as bald, that France may have a king, that kings can be bald, and that the present king of France is bald.

II - The UNL must be language-independent

The linguistic neutrality of the UNL is one of its most imperative and strong commitments and must be understood in its two different senses: the political and the technical. Politically, the UNL is expected to be the language of the United Nations and, therefore, must not be circumscribed to any existing natural language in particular, under the risk of being rejected by the state members of the General Assembly. Technically, the UNL document must be independent from both the source and the target languages. In the UNL approach, there are two basic movements: UNLization and NLization. UNLization is the process of representing the information conveyed by natural language into UNL; NLization, conversely, is the process of generating a natural language document out of UNL. These processes should be completely independent, i.e., the UNLization should not take into consideration which will be the target language of any future NLization; and the NLization should not need any information about the original source language of the UNLization. This means that the UNL representation must be language-independent and, for that reason, should be as semantically complete and saturated as possible.

III - The UNL must be general-purpose

At first glance, the UNL seems to be an "interlingua", a sort of pivot-language to which the source texts are converted before being translated into the target languages. It can, in fact, be used for such a purpose, but its primary objective is to serve as an infrastructure for handling knowledge rather than individual languages. In addition to translation, the UNL is expected to be used in several other different tasks, such as text mining, multilingual document generation, summarization, text simplification, information retrieval and extraction, sentiment analysis etc. Indeed, in UNL-based systems there is no need for the source language to be different from the target language: an English text may be represented in UNL in order to be generated, once again, in English, as a summarized, a simplified, a localized or a simply rephrased version of the original.

IV - The UNL must be machine-tractable

The UNL is a formal system designed for computers. It is an artificial language shaped to represent knowledge in a machine-tractable format. Like other logical systems, it seeks to provide the linguistic and semiotic infrastructure for computers to handle what is meant by natural languages. Differently from other auxiliary languages (such as Esperanto, Interlingua, Volapük, Ido and others), the UNL is not intended to be a human language. We do not expect people to speak UNL or to communicate in UNL. And it must be opaque to the end users. As no one is required to know HTML to browse the Internet or even to create websites, everyone should be able to write and read documents in UNL without any knowledge of UNL.

Scope and Goals

The UNL is an artificial language for representing, describing, summarizing, refining, storing and disseminating information in a natural-language-independent format. It is a kind of mark-up language which represents not the formatting but the core information of a text. As HTML annotations can be realized differently in the context of different applications, machines, displays, etc., so UNL expressions can have different realizations in different human languages. The UNL was conceived at the Institute of Advanced Studies of the United Nations University. It is a property of the United Nations and, therefore, an asset of all of humankind.

The UNL is an effort to achieve a simple basis for representing the most central aspects of information and meaning in a human-language-independent form. As a knowledge representation language, the UNL aims at coding, storing, disseminating and retrieving information independently of the original language in which it was expressed. In this sense, the UNL seeks to provide the tools for overcoming the language barrier in a systematic way.

At first glance, the UNL seems to be an “interlingua”, a sort of pivot-language to which the source texts are converted before being translated into the target languages. It can, in fact, be used for such a purpose, but its primary objective is to serve as an infrastructure for handling knowledge rather than individual languages.

In the UNL approach, there are two basic different movements: UNL-ization and NL-ization. UNL-ization is the process of representing/mapping/analysing the information conveyed by natural language utterances into UNL; NL-ization, conversely, is the process of realizing/manifesting/generating a natural language document out of a UNL graph. These processes are completely independent. For the time being, the NL-ization process has been already fully automatic, whereas the UNL-ization process is still mostly human, even though machine-aided.

Currently, the main goal of the UNL-ization process has been to map the information that is verbally elicited in the surface structure of written texts into a language-independent and machine-tractable database. This means that the UNL representation has not been committed to replicate the lexical and the syntactic choices of the original, but focuses in representing, in a non-ambiguous format, one of its possible readings, preferably the most conventional one. In this sense, the UNL representation has been an interpretation rather than a translation of a given text.

Indeed, it is important to note that at this point in time it would be foolish to state it possible to represent the “full” meaning of any word, sentence or text for any language. Subtleties of intention and interpretation make the “full meaning”, whatever concept we might have of it, too variable and subjective for any systematic treatment. The UNL avoids the pitfalls of trying to represent the “full meaning” of sentences or texts, targeting instead the “core” or “consensual” meaning that is most often attributed to them. In this sense, much of the subtlety of poetry, metaphor, figurative language, inuendo and other complex, indirect communicative behaviours is beyond the current scope and goals of the UNL. Instead, the UNL targets direct communicative behaviour and literal meanings as a tangible, concrete basis for much or most of human communication in practical, day-to-day settings.

This is the main reason why UNL has not been exactly a interlingua-based machine translation project, even though machine translation is one of the possible and more obvious and promising uses of UNL. The main problem is that the practice of translation has been normally restricted to the notion of "fidelity" (or faithfulness), i.e., any translated version of a text is expected to be a replica, in another language, of the content and of the form of the original. This transfer process, however, is “all too human”, as Nietzsche said, to be replicated by the currently existing technology, which is not prepared to deal with several linguistic and cultural phenomena, such as vagueness, ambiguities, metaphors, presuppositions, ellipses, implicatures and so on. This does not mean that natural language automatic processing, and therefore machine translation, is impracticable; it just means that it is not possible yet to do that completely without humans or in the same way humans do. The results, in any case, are likely to be different from the ones produced by humans. Several techniques (rule-based, memory-based, corpus-based) have been proposed to decrease the role of humans in natural language analyses tasks, but the results, even though already promising, are not of publishing-quality yet, and require substantial human revision.

In addition to translation, the UNL has been exploited for several other different tasks in natural language engineering, such as multilingual document generation, summarization, text simplification, information retrieval and semantic reasoning. Indeed, in UNL-based applications there is no need for the source language to be different from the target one: an English text may be represented in UNL in order to be generated, once again, in English, as a summarized, a simplified or a simply rephrased version of the original.

Finally, it should also be stressed that UNL, differently from other auxiliary languages (such as Esperanto, Interlingua, Volapük, Ido and others), is not intended to be a human language. We do not expect people to speak UNL or to communicate "in" UNL; we do expect them to use UNL and to communicate "through" UNL, but in the same unconscious, invisible and spontaneous way they do with other declarative and procedural languages which are pervasive in everyday applications. As no one is required to know HTML to browse the Internet or even to create websites, everyone would be able to UNL-ize documents and to extract out of them the information needed without any knowledge of UNL. UNL is therefore a formal language designed for computers, not for humans. Like other logical systems, it seeks to provide the linguistic and semiotic infrastructure for computers (and not for humans) to handle what is meant by natural languages.

Structure

In the UNL approach, information conveyed by natural language is represented as a hypergraph composed of a set of directed binary labelled 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:

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 here in English words in order to be 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 is organized in an ontology-like structure (the so-called "UNL Ontology"), are defined in the UNL Knowledge Base (UNLKB), and are exemplified in the UNL Example Base (UNLEB).

Relations are expected to represent semantic links between concepts or sets of concepts 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 other closed class categories.