System for natural language understanding

1. A machine-implemented clause mapping method to expand an input of semantically-interpretable syntactic representation(SISR) set of clauses obtained from a digitally encoded natural language source text and from an SISR knowledge base clauses related to the source text, into an output target set of clauses in SISR format, for natural language understanding (NLU),

wherein a lexicon data base comprising SISR semantic lexicons is accessed in the process of the said clause mapping,

wherein the SISR of a natural language (NL) text is a representation of standard templates and fields, wherein each of the existent clauses of the said NL text is represented in a single SISR entry, wherein each clause of the said existent clauses is represented in its complete, independent and declarative form and in the active voice, and in a complement-free (unless obligatory) manner and without the linking expressions and the conjunctions external to the clause and represented also in terms of units, wherein a unit comprises one or more words,

and wherein each SISR entry comprises:

An entry identifier

A clause of the said existent clauses

The complements of the clause of the said existent clauses, represented in terms of the said units

Annotations

wherein the said annotations are data comprising information related the SISR entry and its components,

wherein an SISR semantic lexicon is a lexicon having a list of SISR clauses entries on one side (list side) and corresponding one or more meaning of each clause of the said list in one or more SISR entries for each meaning on the other side (meaning side),

wherein a clause entry on the list side has at least one variable unit in common with a at least one clause entry of every one of the meaning entries on the meaning side,

wherein a variable unit symbolizes a unit category,

said method comprising steps of:

(a) determining relevant SISR semantic lexicons in a lexicon data base and searching for matching entries in the relevant lexicons for an input set of clauses in SISR format, (entry searching step)

(b) selecting for each variable unit in the SISR clauses matched in step (a) its corresponding literal in the clauses of the input set, (symbol substitution step)

(c) computing using the output of step (b) a plurality of clause annotations and generating a set of clauses in SISR format, (clause optimizing step)

(d) adding the output of step (c) together with the input to the target set,

(e) performing multiple iterations of steps (a) through (d) by feeding back the target set as input to step (a), and

(f) generating the target set as output once steps (a) through (e) are completed.

2. The clause mapping method of claim 1 wherein the lexicon database comprises end terms SISR semantic lexicons,

wherein an end terms SISR semantic lexicon is a lexicon having end term clauses on the mapping side and not having end term clauses on the list side,

wherein an end term clause is a clause banned from mapping.

3. The clause mapping method of claim 2 wherein the SISR semantic lexicons comprises a non copula verb clause lexicon.

4. The clause mapping method of claim 2 wherein the SISR semantic lexicons further comprises a complement lexicon.

5. The clause mapping method of claim 2 wherein the SISR semantic lexicons further comprises an adjectives lexicon.

6. The clause mapping method of claim 2 wherein the SISR semantic lexicons further comprises a superlative adjective lexicon.

7. The clause mapping method of claim 2 wherein the SISR semantic lexicons further comprises a comparative adjectives lexicon.