Patent EP0889417A2 successfully refreshed from Google Patents.
EP0889417A2
Expired / Lapsed
EP
⏱️ 0.0 years remaining
Text genre identification
Assignee: Xerox Corp
•
Filing: 1998-07-01
•
Granted: —
•
Expires: 2018-07-01
Abstract
Abstract A processor implemented method of identifying the genre of a machine readable, untagged text. The processor implemented method begins by generating a cue vector from the text, which represents occurrences in the text of a first set of nonstructural, surface cues, which are easily computable. Afterward, the processor determines whether the text is an instance of a first text genre using the cue vector and a weighting vector associated with the first text genre.
Inventors
- 👤 Geoffrey D. Nunberg
- 👤 Jan O. Pedersen
- 👤 Hinrich Schuetze
- 👤 Brett L. Kessler
- 👤 Gregory Grefenstette
Bibliographic Details
Application Number
—
Jurisdiction
EP
Data Source
google_patents
Last Synchronized
2026-10-26 21:19
CPC Classifications
G; G06; G06F; G06F16/00; G06F16/30; G06F16/35; G06F16/353; G06F40/00; G06F40/20; G06F40/205; G06F40/211; G06F40/279; G06F40/284; G06F40/289; G06F40/30
Claims Analysis
Total Claims: 10
Claim 1
Independent Claim
81 words
A processor implemented method of identifying a text
genre of an untagged text in machine-readable form without
structurally analyzing the text, the processor implemented
method comprising the steps of: a) generating a cue vector from the text, the cue
vector representing occurrences in the text of a first set
of nonstructural, surface cues; and b) determining whether the text is an instance of a
first text genre using the cue vector and a weighting
vector associated with the first text genre.
Claim 2
Dependent Claim
109 words
A processor implemented method of identifying a text
genre of an untagged text in machine-readable form without
structurally analyzing the text, the processor implemented
method comprising the steps of: a) generating a cue vector from the text, the cue
vector representing occurrences in the text of a first set
of nonstructural, surface cues; b) determining a relevancy to the text of each facet
of a second set of facets using the cue vector and a
weighting vector; and c) identifying from a third set of text genre types
a text genre type of the text based upon those facets of
the second set that are relevant to the text.
Claim 3
Dependent Claim
42 words
A method according to claim 2, wherein the second set
of facets includes at least a one of a date facet, a
narrative facet, a suasive facet, a fiction facet, a legal
facet, a science and technical facet, and an author facet.
Claim 4
Dependent Claim
39 words
A method according to claim 2 or claim 3, wherein the
third set of text genre types includes at least a one of a
press report type, an Email type, an editorial opinion
type, and a market analysis type.
Claim 5
Independent Claim
36 words
A method according to any of the preceding claims,
wherein the first set of cues includes one of a
punctuational cue, a lexical cue, a string recognizable
constructional cue, a formulae cue and a deviation cue.
Claim 6
Dependent Claim
44 words
A method according to claim 5, wherein the
punctuational cue represents a one of a number of commas in
the text, a number of dashes in the text, a number of
question marks in the text and a number of semi-colons in
the text.
Claim 7
Dependent Claim
58 words
A method according to claim 5 or claim 6, wherein the
lexical cue represents a one of a first number of
occurrences in the text of acronyms, a second number of
occurrences in the text of modal auxiliaries, a third
number of occurrences of form of the verb "be", and a
fourth number of occurrences of calender words.
Claim 8
Independent Claim
39 words
A method according to any of claims 5 to 7, wherein
the deviation cue includes a one of a first deviation of a
sentence length of the text and a second deviation of a
word length of the text.
Claim 9
Independent Claim
54 words
A method according to any of claims 5 to 8, wherein
the string recognizable constructional cue includes at
least one string recognizable constructional cue
representing a one of a first number of sentences starting
with the words "and", "but" and "so" and a second number of
sentences starting with an adverb and a comma.
Claim 10
Dependent Claim
15 words
A processor programmed to carry out a method according
to any of the preceding claims.
References Cited (Backward Citations)
No citation records indexed.
USPTO Annuity & Maintenance Windows
Maintenance schedule is calculated for granted US utility patents.