System for natural language understanding

• US 9,710,458 B2
• Filed: 07/08/2015
• Issued: 07/18/2017
• Est. Priority Date: 04/01/2011
• Status: Active Grant

• Current Assignee: Maan Ghannam, Rima Ghannam
• Original Assignee: Maan Ghannam, Rima Ghannam
• Inventors: Ghannam, Maan, Ghannam, Rima
• Primary Examiner(s): COLUCCI, MICHAEL C
• Application Number:
  US14/793,760
• Publication Number:
  US 20160041967A1
• Time in Patent Office: 741 Days
• Field of Search: 704 9, 704 8, 704 4, 704 3, 704 2, 704 10, 715230, 715236, 7079991
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: G06F 40/169 Annotation, e.g. comment data or footnotes
• CPC Class Codes: G06F 40/186 Templates
• CPC Class Codes: G06F 40/211 Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30

Abstract

A general-purpose apparatus for analyzing natural language text that allows for the implementation of a broad range of natural language understanding applications. The apparatus for natural language understanding analyzes a source text and transforms the source text into a semantically-interpretable syntactic representation (SISR), comprising a syntax template and semantic clause annotations. The general-purpose apparatus for natural language understanding is adaptable to various source text natural languages and is adaptable to various natural language understanding applications, such as query answering, translation, summarization, information extraction, disambiguation, and parsing. A natural language query answering apparatus for answering questions about a source text, whereby the query answering apparatus utilizes the general-purpose apparatus for transforming the natural language query into SISR format.

Claims

1. A general-purpose computing machinery apparatus for natural language understanding (NLU), wherein said apparatus accepts a digital natural language source text and outputs a target representation of the source text in a semantically-interpretable syntactic representation (SISR) form, said apparatus comprising:

a parser component that accepts the source text which is unstructured data and generates by processors an output of structured data in a SISR form;

a searcher component that accepts the parser output and generates a SISR of facts encoded in a knowledge base relevant to the SISR of the source text; and

a clause mapping component that receives the output of the parser and the output of the server and generates the target representation;

wherein the SISR of a natural language (NL) text is an outcome of a reverse engineering process of sentences construction, wherein in the said process, a sentence that is presumed to be constructed out of initial independent clauses through various operations as modifications of the said initial independent clauses and words addition (linking expressions) is worked out to identify the said initial independent clauses and added words, wherein SISR is a structured representation of standard templates and fields, wherein each initial independent clause existent in the said NL text is represented in a single entry, wherein each clause of the existent clauses in the said NL text 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 any conjunctions external to the clause and represented also in terms of units, wherein a unit comprises one or more words able to be associated together to represent a grammatical function as noun, verb, preposition, verbal phrase, adjective, comparative adjective, superlative adjective, superlative adverb, comparative adverb, or copula, and wherein each entry comprises;

an entry identifier;

a clause of the said existent clauses represented in terms of the said units in a syntax template;

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

annotations;

wherein the said annotations are data comprising information related to the entry and its components;

wherein the said annotations are data comprising information related to the entry and its components, and wherein the target representation is an expanded SISR containing further semantic information of the SISR of the source text and the SISR facts.

2. The apparatus of claim 1 further comprising a lexicon database, the lexicon database comprising:

a plurality of lexicons and a plurality of lists, wherein the lexicon database is configured to receive lookup requests from the source parser and wherein the lexicon database is configured to receive lookup requests from the clause mapping component.

3. The apparatus of claim 2, wherein the lexicon database further comprises a noun-categories lexicon where each left side entry is a noun corresponding to a right side entry that lists the possible semantic categories proper to the noun.

4. The apparatus of claim 2, wherein the lexicon database further comprises a semantic non-copula verb clauses lexicon where each left side entry of non copula category template clauses corresponds to one or more right side representations.

5. The apparatus of claim 4, wherein a right side entry of the semantic non-copula verb clauses lexicon contains an equal or less number of end-terms clauses than the number of end-terms clauses in the corresponding left side entry, wherein an end-term clause is a clause that does not get subjected to mapping.

6. The apparatus of claim 4, wherein the right side entry of the semantic non-copula verb clauses lexicon comprises:

a clause that describes the status of the subject or object before the application of the verb unit of the clause; and

a clause that describes the status of the subject or object after the application of the verb unit of the clause.

7. The apparatus of claim 4, wherein the right side entry of the semantic non-copula verb clauses lexicon expresses the assumed condition of the corresponding left side entry.

8. The apparatus of claim 4, wherein the right side entry of the semantic non-copula verb clauses lexicon states the assumed fact of the corresponding left side entry.

9. The apparatus of claim 4, wherein the right side entry of the semantic non-copula verb clauses lexicon comprises a neutral flag wherein the said neutral flag is set when the corresponding left side entry should not be treated as a ground truth.

10. The apparatus of claim 4, wherein the right side entry of the semantic non-copula verb clauses lexicon expresses a literal performance of the unit verb of the corresponding left side entry.

11. The apparatus of claim 4, wherein the right side entry of the semantic non-copula verb clauses lexicon expresses an assumed noun of the corresponding left side entry.

12. The apparatus of claim 2, wherein the lexicon database further comprises a semantic complements lexicon wherein the said lexicon consists of left side entries of clause prototype and complement type combination and the right side corresponding to one or more representations, where each representation consists of one or more complement free clauses and annotations.

13. The apparatus of claim 2, wherein the lexicon database further comprises a semantic adjective lexicon wherein the said lexicon consists of left side entries of adjective template clause and one or more right side corresponding representations, where each representation consists of clauses that don'"'"'t have any adjective units other than base adjectives, wherein a base adjective is an adjective which if present in a clause then the clause is considered end-term clause provided that it cannot be mapped due to any other constituent distinct from said adjective.

14. The apparatus of claim 2, wherein the lexicon database further comprises a semantic comparative adjective lexicon wherein the said lexicon consists of left side entries of comparative adjective template clause and one or more right side corresponding representations.

15. The apparatus of claim 14, wherein each right side entry corresponding to a left side entry comprises three clauses, a first clause assigning a variable indicating a measure to one of the compared poles, a second clause assigning another similar variable to the second item of the compared poles;

and a third clause representing a comparison between the two variables using a comparative adjective out of the base comparative adjectives list that is a base adjective.

16. The apparatus of claim 2, wherein the lexicon database further comprises a semantic superlative adjective lexicon wherein the said lexicon consists of left side entries of superlative adjective template clause and one or more right side corresponding representations.

17. The apparatus of claim 16, wherein each right side entry corresponding to a left side entry comprises three clauses:

a first conditional clause expressing whether a variable element belongs to the comparison set pointed by a superlative adjective;

a second conditional clause expressing whether the said variable element is different from the subject of the initial clause applied when the first clause is true; and

a third clause that responds to the second clause and shows a relation of comparative adjective type between the subject and the variable element.

18. The apparatus of claim 2, wherein the lexicon database further comprises a lexicon mapping verbs to their corresponding time nature, where the time nature is one of instantaneous, span, or absolute.

19. The apparatus of claim 2, wherein the lexicon database further comprises a semantic lexicon of prototypes of consecutive noun phrases wherein each left side entry of noun phrases template prototype having consecutive simple noun phrases or nouns separated by propositions corresponds to a right side equivalent clause template, wherein equivalent clause template is built upon simplified nouns and their pre-modification words.

20. The apparatus of claim 2, wherein the lexicon database further comprises a semantic lexicon of the pre-modification words in a simple noun phrase wherein the said lexicon consists of left side entries of simple noun phrases template and the right side corresponding representation that consists of one or more equivalent clause templates.

21. The apparatus of claim 2, wherein the lexicon database further comprises a semantic lexicon of nominal compounds wherein the said lexicon consists of left side entries of two words nominal compounds and corresponding right side entries of clauses templates stating an equivalent meaning of the two words nominal compounds.

22. The apparatus of claim 2, wherein the lexicon database further comprises a linking expressions lexicon, wherein each left side linking expressions occurrence prototypes corresponds to a right side representation of the matching annotations and clauses.

23. The apparatus of claim 2, wherein the lexicon database further comprises an idioms lexicon wherein each left side entry of idiom, interjection or metonym corresponds to a right side of the equivalent meaning representation.

24. The apparatus of claim 2, wherein the lexicon database further comprises a list of various clause prototypes.

25. The apparatus of claim 2, wherein the lexicon database further comprises a base template clause type list, wherein a clause that corresponds to a base template clause is an end term clause.

26. The apparatus of claim 2 wherein the lexicon database further comprises a base adjective list.

27. The apparatus of claim 2 wherein the lexicon database further comprises a list of comparative adjectives that have a transitive property.

28. The apparatus of claim 2 wherein the lexicon database further comprises a list of prepositional phrase combinations that have a transitive property.

29. The apparatus of claim 1 wherein the said annotations of the entry clause comprise:

a time limit annotation, specifying the time limits of the action of the entry clause, a field denoting whether the clause is originally a complement of another clause, a field denoting the identifier of a clause the entry clause is a complement of (if any), a field denoting the syntax template prototype, a field denoting whether the entry clause is from the original source text or derived in subsequent analysis, a field denoting the beginning time of the verb of the entry clause, a field denoting the end time of the verb of the entry clause, a field denoting the time nature of the verb of the entry clause, a field denoting the initial position in the entry clause of a complement, a field denoting the tense of the verb of the entry clause, a field denoting whether the entry clause itself or its root is derived from the knowledge base or the input source, a field denoting whether the entry clause is a conditional (e.g., if-then) expression, a field denoting the entry clause'"'"'s associated conjunction, fields denoting the clauses to which the entry clause is linked to, a field denoting type of the link, a field denoting any linking expression, fields denoting the other clauses issued along with the entry clause out of the original sentence, a field denoting whether the entry clause was originally a dependent or independent clause in the sentence, a field denoting the initial clause form (declarative, interrogative, imperative), a field denoting the initial clause voice (passive, active), a field denoting the corresponding clause prototype of the verbal phrase complement, a field denoting the clause'"'"'s context (information that could be obtained with the input), a field denoting the corresponding prototype of the verbal phrase complement, a field denoting the clause that the current clause is issued from (upon mapping) in case it is so.