Computer based summarization of natural language documents

• US 7,251,781 B2
• Filed: 07/31/2002
• Issued: 07/31/2007
• Est. Priority Date: 07/31/2001
• Status: Expired due to Term

• Current Assignee: Allium US Holding LLC
• Original Assignee: Invention Machine Corporation (S&P Global Inc.)
• Inventors: Tsourikov, Valery, Sovpel, Igor, Batchilo, Leonid
• Primary Examiner(s): Hutton; Doug
• Assistant Examiner(s): RUTLEDGE, AMELIA L
• Application Number:
  US10/208,941
• Publication Number:
  US 20030130837A1
• Time in Patent Office: 1,826 Days
• Field of Search: 715/531, 715/530, 715/511, 704/9
• US Class Current: 715/210
• CPC Class Codes: G06F 16/345 Summarisation for human users
• CPC Class Codes: G06F 40/216 using statistical methods
• CPC Class Codes: G06F 40/253 Grammatical analysis; Style critique
• CPC Class Codes: G06F 40/30 Semantic analysis

Abstract

A system and method for summarizing the contents of a natural language document provided in electronic or digital form includes preformatting the document, performing linguistic analysis, weighting each sentence in the document as a function of quantitative importance, and generating one or more document summaries, from a plurality of selectable document summary types, as a function of the sentence weights.

Claims

1. A method for summarizing the contents of a natural language document including a plurality of sentences and provided in electronic or digital form, said method comprising:

A. extracting words from sentences in said document, including determining knowledge at a fact level for each sentence by;

i) identifying the words within the sentence as parts of speech in the form of eSAOs, including identifying the words as at least one of subjects, objects, actions, adjectives, prepositions, indirect objects and adverbials; and

ii) determining if Cause-Effect relationships exist in the sentence based on semantic relationships between eSAOs in the sentence;

B. determining a weight for each eSAO and a Cause-Effect weight for each Cause-Effect relationship;

C. determining a sentence weight for each sentence in said document, using the weights of all eSAOs for said sentence and, if the sentence has a Cause-Effect relationship, the Cause-Effect weight for each Cause-Effect relationship in the sentence; and

D. generating one or more weight-based document summaries as a function of said sentence weights and at least one of displaying the summaries to a user and storing the summaries to a memory.

2. The method of claim 1, further including in step A determining attributes for at least some of said subjects, objects, and indirect objects, wherein an attribute represents a word or phrase having a relationship to the subject, object, or indirect object for which it is an attribute.

3. The method of claim 2, wherein said relationship is one or more of a feature, inclusion, placement, formation, connection, separation, or transfer.

4. The method of claim 3, wherein said relationship is a feature of a type of parameter.

5. The method of claim 1, wherein step A includes using Recognizing Linguistic Models to detect said semantic relationships between said eSAOs, wherein said Recognizing Linguistic Models describe algorithms for detecting said Cause-Effect relationships between said eSAOs using linguistic patterns, lexemes and predefined codes or tags from a list of codes or tags.

6. The method of claim 1, wherein step B is accomplished using statistical weighting, including determining said eSAO weight as a function of the frequency of appearance of components of said eSAOs in said document.

7. The method of claim 6, wherein the statistical weight of said sentence is a function of the maximum weight of each eSAO in said sentence.

8. The method of claim 1, further including determining a cue weight for each sentence using cue weighting, including determining said cue weight as a function of a quantitative importance of assigned to words and phrases, wherein said sentence weights are further determined as a function of said cue weights.

9. The method of claim 8, further including determining the Cause-Effect weight for each sentence using Cause-Effect weighting, including determining said Cause-Effect weight as a function of a quantitative score assigned to words and phrases having the Cause-Effect relationship.

10. The method of claim 1, further including determining the Cause-Effect weight for each sentence using Cause-Effect weighting, including determining said Cause-Effect weight as a function of a quantitative score assigned to words and phrases having a Cause-Effect relationship.

11. The method of claim 1, wherein one or more document summaries are selectable from a set of document summary types including at least one of a key-word summary, a topic-oriented summary, an eSAO summary, a classic summary, and a field-oriented summary.

12. The method of claim 1, wherein step D includes contracting said one or more weight-based document summaries by deleting introductory phrases and sentences as a function of a set of document patterns, wherein said document patterns identify said introductory phrases and sentences as having low relevance.

13. A method for summarizing the contents of a natural language document provided in electronic or digital form, said method comprising:

A. performing linguistic analysis, including;

i) extracting words from sentences in said document, including determining knowledge at a fact level for each sentence by;

a. identifying the words within the sentence as parts of speech in the form of eSAOs, including identifying the words as at least one of subjects, objects, and actions, and tagging substantially each word as a function of a part of speech of said word; and

b. determining if Cause-Effect relationships exist in the sentence based on semantic relationships between eSAOs in the sentence;

ii) parsing verbal sequences and noun phrases from said tagged words; and

iii) building a syntactical parsed tree from said verbal sequences and noun phrases, according to a set of rules, wherein words grouped by a rule become inaccessible to other rules;

B. weighting each sentence in the document as a function of quantitative importance and said syntactical parsed tree, including determining a Cause-Effect weight for each Cause-Effect relationship in the sentence; and

C. generating one or more weight-based document summaries, from a plurality of selectable document summary types, as a function of the sentence weights and at least one of displaying the summaries to a user and storing the summaries to a memory.

14. The method claim 13, further comprising, before step A:

D. preformatting the document, including;

i) removing symbols that are not part of the natural language text;

ii) correcting mismatches and misspellings;

iii) dividing the document into words and sentences; and

iv) recognizing document fields.

15. The method of claim 13, wherein the form of eSAOs in step A further includes one or more of adjectives, prepositions, indirect objects and adverbials.

16. The method of claim 13, wherein step B includes determining a weight for each eSAO.

17. The method of claim 13, wherein step B includes determining a cue weight for each sentence.

18. A system for summarizing the contents of a natural language document provided in electronic or digital form, said system comprising:

A. at least one memory having a set of linguistic rules stored therein;

B. a linguistic analyzer coupled to said at least one memory and configured to;

i) extract words from sentences in said document, including determining knowledge at a fact level for each sentence by;

a. identifying the words within the sentence as parts of speech in the form of eSAOs, including identifying the words as at least one of subjects, objects, and actions, and tagging substantially each word as a function of a part of speech of said word; and

b. determining if Cause-Effect relationships exist in the sentence based on semantic relationships between eSAOs in the sentence;

ii) parsing verbal sequences and noun phrases from said tagged words; and

iii) building a syntactical parsed tree from said verbal sequences and noun phrases, according to said set of rules, wherein words grouped by a rule become inaccessible to other rules;

C. a sentence weighting module configured to access said syntactical phrase tree and to determine a weight tbr each sentence in the document as a function of quantitative importance and said syntactical parsed tree and if the sentence has a Cause-Effect relationship, determine the Cause-Effect weight for each Cause-Effect relationship in the sentence; and

D. a summary generator configured to generate one or more weight-based document summaries, from a plurality of selectable document summary types, as a function of the sentence weights.

19. The system as in claim 18, further comprising:

E. a preformatter configured for;

i) removing symbols that are not part of the natural language text;

ii) correcting mismatches and misspellings;

iii) dividing the document into words and sentences; and

iv) recognizing document fields.

20. The system of claim 18, wherein the form of eSAOs further includes one or more of adjectives, prepositions, indirect objects and adverbials.

21. The system of claim 18, wherein said sentence weighting module is further configured for determining a weight for each eSAO.

22. The system of claim 18, wherein said sentence weighting module is further configured for determining a cue weight for each sentence.

23. A system for summarizing the contents of a natural language document including a plurality of sentences and provided in electronic or digital form, said system comprising:

A. at least one memory having a set of linguistic rules stored therein;

B. a linguistic analyzer coupled to said at least one memory and configured to extract words from sentences in said document, including determining knowledge at a fact level for each sentence by;

i. identifying the words within the sentence as parts of speech in the form of eSAOs, including subjects, objects, actions, adjectives, prepositions, indirect objects and adverbials; and

ii. determining if Cause-Effect relationships exist in the sentence based on semantic relationships between eSAOs in the sentence;

C. a weighting module configured to determine a weight for each eSAO and a Cause-Effect weight for each Cause-Effect relationship and, to determine a sentence weight for each sentence in said document, using the weights of all eSAOs for said sentence and, if the sentence has a Cause-Effect relationship, the Cause-Effect weight for each Cause-Effect relationship in the sentence; and

D. a summary generator configured to generate one or more weight-based document summaries as a function of said sentence weights.

24. The system of claim 23, wherein said linguistic analyzer is further configured for determining attributes for at least some of said subjects, objects, and indirect objects, wherein an attribute represents a word or phrase having a relationship to the subject, object, or indirect object for which it is an attribute.

25. The system of claim 24, wherein said relationship is one or more of a feature, inclusion, placement, formation, connection, separation, or transfer.

26. The system of claim 25, wherein said relationship is a feature of a type of parameter.

27. The system claim 23, wherein said linquistic analyzer is further configured for determining Cause-Effect relationships between said eSAOs, wherein a Cause-Effect relations recognizer uses Recognizing Linauistic Models to detect said semantic relationships between said eSAOs, and wherein said Recognizing Linguistic Models describe algorithms for detecting said Cause-Effect relationships between said eSAOs using linguistic patterns, lexemes and predefined codes or tags from a list of codes or tags.

28. The system of claim 23, wherein said weighting module is configured for performing statistical weighting, including determining said eSAO weight as a function of the frequency of appearance of components of said eSAO in said document.

29. The system of claim 28, wherein the weight of said sentence is a function of the maximum weight of each eSAO in said sentence.

30. The system of claim 23, wherein said weighting module is further configured for determining a cue weight for each sentence using cue weighting, including determining said cue weight as a function of a quantitative importance of assigned to words and phrases, wherein said sentence weights are further determined as a function of said cue weights.

31. The system of claim 30, wherein said weighting module is further configured for determining the Cause-Effect weight for each sentence using Cause-Effect weighting, including determining said Cause-Effect weight as a function of a quantitative score assigned to words and phrases having a Cause-Effect relationship.

32. The system of claim 23, wherein said weighting module is further configured for determining the Cause-Effect weight for each sentence using Cause-Effect weighting, including determining said Cause-Effect weight as a function of a quantitative score assigned to words and phrases having a Cause-Effect relationship.

33. The system of claim 23, wherein said one or more document summaries are selectable from a set of document summary types including at least one of a key-word summary, a topic-oriented summary, an eSAO summary, a classic summary, and a field-oriented summary.

34. The system of claim 23, wherein said summary generator is further configured for contracting said one or more weight-based document summaries by deleting introductory phrases and sentences as a function of a set of document patterns, wherein said document patterns identify said introductory phrases and sentences as having low relevance.