UNLization

UNLization, formerly known as enconversion, is the process of "representing" a natural language structure into UNL. This "representation" should be understood as a interpretation rather than as a translation of the source document, in the sense it is not necessarily committed to its linguistic structure (such as lexical choice and syntax) but to its semantic structure only (it must replicate concepts and relations between concepts conveyed by the linguistic structure).

UNLization paradigms

The process of UNLization may follow several different paradigms, as follows:

• Language-based UNLization (based mainly in a NL-UNL dictionary and NL-UNL grammar)
• Knowledge-based UNLization (based mainly in the UNL Knowledge Base)
• Example-based UNLization (based mainly in the UNL Example Base))
• Memory-based UNLization (based mainly in the UNL-NL UNlization Memory)
• Statistical-based UNLization (based mainly in statistical predictions derived from UNL-NL corpora)
• Dialogue-based UNLization (based mainly in the interaction with the user)

Recall

• Full UNLization (the whole source document is UNLized)
• Partial (or chunk) UNLization (only a part of the source document, e.g. main clauses, is UNLized)

Precision

• Deep UNLization (the UNLization focus the deep semantic structure of the source document)
• Shallow UNLization (the UNLization focus the surface semantic structure of the source document)

Units

• Word-driven UNLization (the UNLization does not preserve any structure of the source document)
• Sentence-driven UNLization (the UNLization preserves the sentence strucutres of the source document)
• Text-driven UNLization (the UNLization preserves the whole structure of the source document)

Scope

• Locutionary content (the UNLization represents only the literal meaning)
• Ilocutionary content (the UNLization represents also non-literal meanings)

The main difference between both scopes of the UNLization process is that.

onsequence of such assumption is that the UNL document will not contain the semantic ambiguities of the original, and will only encode one of its possible semantic realisations, preferably the most frequent one. This does not mean, however, that UNL is constrained only to the literal meaning or that it is not able to register syntactic phenomena that may affect the interpretation of a given utterance. The UNL Specs contain attributes to represent figures of speech, the functional structure of the sentence, speech acts and other information that may be used to provide not only semantically-equivalent but also functionally-equivalent utterances, as indicated below:

The bank crashed.

UNL is not able to preserve the lexical ambiguity of the word "bank" in the sentence above. The UNL representation will necessarily choose between one of the possible concepts conveyed by the English word "bank".

The boy saw the girl with binoculars

UNL is not able to represent the syntactic ambiguity of the sentence above. The UNL representation will necessarily choose between one of the possible syntactic structures of the sentence.

Mary was killed by Peter

UNL may represent the passive voice by assigning the attribute @passive to the verb

As for the little girl, the dog licked her.

UNL may represent the topicalization of "little girl" by assigning the attribute @topic to it

It is as soft as concrete

UNL may represent the ironical aspect of the sentence above by assigning the attribute @irony to the corresponding representation.

Can you pass me the salt?

UNL may represent the speech act conveyed by the sentence above by assigning the attribute @request to it.