Natural language processing method by analyzing primitive sentences, logical clauses, clause types and verbal blocks

• US 8,706,476 B2
• Filed: 09/18/2007
• Issued: 04/22/2014
• Est. Priority Date: 09/18/2007
• Status: Expired due to Fees

• Current Assignee: Elsevier Incorporated (RELX PLC)
• Original Assignee: Ariadne Genomics, Inc. (RELX PLC)
• Inventors: Daraselia, Nikolai
• Primary Examiner(s): Hudspeth, David R.
• Assistant Examiner(s): Kazeminezhad, Farzad
• Application Number:
  US11/898,952
• Publication Number:
  US 20090076796A1
• Time in Patent Office: 2,408 Days
• Field of Search: 704/9, 364/419
• US Class Current: 704/9
• CPC Class Codes: G06F 40/211 Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
• 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
• CPC Class Codes: G06F 40/55 Rule-based translation
• CPC Class Codes: G06F 9/454 Multi-language systems; Localisation; Internationalisation

Abstract

Methods for converting a natural language sentence into a set of primitive sentences. The method includes identifying verbal blocks in the sentence, splitting the sentence into a set of logical clauses, determining a type of each clause wherein the type of each clause determines whether or not said clause contains verbal blocks, disambiguating ambiguous verbal blocks within each logical Clause, mad constructing a primitive sentence for each verbal block by duplicating the shared noun phrases of verbal blocks.

Claims

1. A method for converting a natural language sentence into a set of primitive sentences, comprising steps:

(a) identifying verbal blocks in the sentence;

(b) splitting the sentence into a set of logical clauses;

(c) determining a type of each clause;

(d) disambiguating ambiguous verbal blocks within each logical clause in which verbal blocks are considered independently of noun phrases; and

(e) constructing a primitive sentence for each verbal block by duplicating the shared noun phrases of verbal blocks; and

wherein the method is performed by a computer system comprising a processor and a non-transitory program storage device readable by the computer system,

wherein the order of step (a) and step (b) is interchangeable,

wherein the primitive sentence is a sentence containing one relation, expressed by a verbal block, between two or more noun phrases, and

wherein the type of each clause determines whether or not said clause contains verbal blocks.

2. A method for extracting information from a natural language sentence, comprising:

converting the sentence into a set of primitive sentences by detecting logical clauses;

determining a type of each clause; and

indexing corpora using at least one primitive sentence,

wherein the method is performed by a computer system comprising a processor and a non-transitory program storage device readable by the computer system,

wherein each primitive sentence is a sentence containing one relation, expressed by a verbal block, between two or more noun phrases, and

wherein the type of each clause determines whether or not said clause contains verbal blocks.

3. A method for extracting information from a natural language sentence, comprising steps:

(a) identifying verbal blocks in the sentence;

(b) splitting the sentence into a set of logical clauses;

(c) determining a type of each clause;

(d) disambiguating ambiguous verbal blocks within each logical clause in which verbal blocks are considered independently of noun phrases;

(e) constructing a primitive sentence for each verbal block by duplicating the shared noun phrases of verbal blocks; and

(f) extracting information from each primitive sentence;

wherein the method is performed by a computer system comprising a processor and a non-transitory program storage device readable by the computer system,

wherein the order of step (a) and step (b) is interchangeable,

wherein the primitive sentence is a sentence containing one relation, expressed by a verbal block, between two or more noun phrases, and

wherein the type of each clause determines whether or not said clause contains verbal blocks.

4. The method of claim 3, wherein information is extracted from each primitive sentence by detecting sequences of words in the primitive sentence using regular expression-like word patterns.

5. A computer system comprising:

a processor; and

a non-transitory program storage device readable by the computer system, embodying a program of instructions executable by the processor to perform method steps for converting a natural language sentence into a set of primitive sentences, comprising;

(a) identifying verbal blocks in the sentence;

(b) splitting the sentence into a set of logical clauses;

(c) determining a type of each clause;

(d) disambiguating ambiguous verbal blocks within each logical clause in which verbal blocks are considered independently of noun phrases; and

(e) constructing a primitive sentence for each verbal block by duplicating the shared noun phrases of verbal blocks;

wherein the order of step (a) and step (b) is interchangeable,

wherein the primitive sentence is a sentence containing one relation, expressed by a verbal block, between two or more noun phrases, and

wherein the type of each clause determines whether or not said clause contains verbal blocks.

6. A computer system comprising:

a processor; and

a non-transitory program storage device readable by the computer system, embodying a program of instructions executable by the processor to perform method steps for extracting information from a natural language sentence, comprising;

converting the sentence into a set of primitive sentences by detecting logical clauses;

determining a type of each clause; and

indexing corpora using at least one primitive sentence,

wherein each primitive sentence is a sentence containing one relation, expressed by a verbal block, between two or more noun phrases, and

wherein the type of each clause determines whether or not said clause contains verbal blocks.

7. A computer system comprising:

a processor; and

a non-transitory program storage device readable by the computer system, embodying a program of instructions executable by the processor to perform method steps for extracting information from a natural language sentence, comprising;

(a) identifying verbal blocks in the sentence;

(b) splitting the sentence into a set of logical clauses;

(c) determining a type of each clause;

(d) disambiguating ambiguous verbal blocks within each logical clause in which verbal blocks are considered independently of noun phrases;

(e) constructing a primitive sentence for each verbal block by duplicating the shared noun phrases of verbal blocks; and

(f) extracting information from each primitive sentence;

wherein the order of step (a) and step (b) is interchangeable,

wherein the primitive sentence is a sentence containing one relation, expressed by a verbal block, between two or more noun phrases, and

wherein the type of each clause determines whether or not said clause contains verbal blocks.

8. A computer system of claim 7, wherein information is extracted from each primitive sentence by detecting specific sequences of words in the primitive sentence using regular expression-like word patterns.