System and method for generating analytic summaries

• US 20020194230A1
• Filed: 06/19/2001
• Published: 12/19/2002
• Est. Priority Date: 06/19/2001
• Status: Active Grant

• Current Assignee: Fujifilm Business Innovation Corp. (Fujifilm Holdings Corporation)
• Original Assignee: Fuji Xerox Company Limited (Xerox Holdings Corp.)
• Inventors: Van Den Berg, Martin Henk, Polanyi, Livia
• Granted Patent: US 7,092,872 B2
• Time in Patent Office: Days
• US Class Current: 704/9
• CPC Class Codes: G06F 16/345 Summarisation for human users
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: G06F 40/289 Phrasal analysis, e.g. finite state techniques or chunking
• CPC Class Codes: G06F 40/30 Semantic analysis

Abstract

A technique for compressing texts such that referential integrity, sentence coherency, punctuation and readability are preserved and which provides for compression of sentence constituents based on the type of content, the informativity of the sentence constituent and the grammatical readability of the resultant sentence or phrase. Information content portions are parsed to generate parts of speech tags. The informativity of the constituents in a phrase or sentence is determined and the parts of speech having lower information content and having a low effect on grammatical readability of the phrase or sentence are selectively compressed. Parts of speech having successively higher informativity and low effect on grammatical readability are selected for compression until the desired level of compression is reached. Compressed portions are indicated in the summary with a selectable placeholder which expands to display the compressed text.

Claims

1. A system for generating text summaries of a content portion comprising at least one phrase, the system comprising:

a parts of speech determining circuit that determines the part of speech of constituents of the at least one phrase;

an informativity determining circuit that determines the informativity of the constituents of the at least one phrase based on the determined part of speech;

an informativity compressing circuit that compresses the constituents of the at least one phrase based on the determined informativity, grammatical readability and a desired degree of compression.

2. The system of claim 1, wherein the informativity compressing circuit comprises at least one of a prepositional/adverbial temporal phrase compressing circuit, a prepositional/adverbial phrase of manner compressing circuit, a prepositional/adverbial phrase of location compressing circuit, a consecutive adjective compressing circuit, a consecutive adverb compressing circuit, an intensifying adverb compressing circuit, an enumerating adverb compressing circuit, a consecutive determiner compressing circuit and an expletive connective adverb compressing circuit.

3. The system of claim 2, further comprising a subordinate clause compressing circuit.

4. The system of claim 1, wherein the at least one content portions are text summaries generated by an alternate text summary generating system.

5. The system of claim 1, wherein the parts of speech determining circuit comprises at least one of a shallow syntactic parser, a deep parser, a tagger and a lexicon.

6. The system of claim 2, wherein the expletive connective adverb compressing circuit further comprises a verb adjustment circuit.

7. The system of claim 1, wherein the informativity compressing circuit further compresses the constituents of the at least one phrase based on the determined informativity, a desired degree of compression and a text type of the content portion.

8. A method for generating text summaries of a content portion comprising at least one phrase, the method comprising the steps of:

determining a desired degree of compression;

determining parts of speech of the constituents of the at least one phrase;

determining the informativity of the constituents of the at least one phrase based on the determined part of speech;

compressing the constituent of the at least one phrase based in the determined informativity, grammatical readability and the desired degree of compression.

9. The method of claim 8, wherein determining the informativity comprises determining at least one of a prepositional/adverbial temporal phrase, a prepositional/adverbial phrase of manner, a prepositional/adverbial phrase, a consecutive adjective, a consecutive adverb, an intensifying adverb, an enumerating adverb, a consecutive determiner and an expletive connective adverb.

10. The method of claim 9, further comprising compressing subordinate clauses.

11. The method of claim 8, wherein the at least one content portion is a text summary generated by an alternative text summary generating system.

12. The system of claim 8, wherein determining the part of speech comprises shallow syntactic parsing, deep parsing and tagging.

13. The method of claim 9, wherein determining the expletive connective adverb further comprises adjusting the verbs in the phrase.

14. The method of claim 8, further comprising compressing the constituent of the at least one phrase based on the determined informativity, the desired degree of compression and a text type of the content portion.