US5652898A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Dictionary memory for text processing using word frequency and word recency occurrence information
Assignee: Hitachi Ltd
•
Filing: 1993-08-31
•
Granted: 1997-07-29
•
Expires: 2013-08-31
Abstract
Abstract A dictionary memory acquires knowledge of degrees of association between words. Word units are provided, each corresponding to a word and each storing word occurrence information, and these word units are connected by links in which the degree of association between words is stored, forming a network. The word units use word occurrence information to determine the degrees of activity of words, links determine word expectations based on the degrees of activity and degrees of association between words, and the word units determine likelihoods of words in input registers by adding the expectations thereto. Next, words selected by a maximum-likelihood word selecting part are placed in an output register by the corresponding word units. Links adjust degrees of association between words based on the likelihoods and degrees of activity of words.
Inventors
- 👤 Hiroyuki Kaji
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-07 15:09
CPC Classifications
G; G06; G06F; G06F40/00; G06F40/20; G06F40/237; G06F40/242; G06F40/279; G06F40/284; G06F40/40; G06F40/42; G06F40/47
Claims Analysis
Total Claims: 11
Claim 1
Independent Claim
65 words
A dictionary memory comprises a network constituted by word units each of which corresponds to a word and has means for storing information on the frequency of occurrence and recency of occurrence of the corresponding word in a text, and links each of which corresponds to a pair of words and has means for storing the degree of association between the corresponding pair of words.
Claim 2
Dependent Claim
65 words
A dictionary memory comprises a network constituted by word units each of which corresponds to a word and has means for storing information on the frequency of occurrence and recency of occurrence of the corresponding word in a text, and links each of which corresponds to a pair of words and has means for storing the degree of association between the corresponding pair of words.
Claim 3
Dependent Claim
53 words
A dictionary memory, comprising: means for storing a degree of association between words; means for storing information on occurrence of words in a text; and means for determining a degree of activity of a word based on information on the frequency of occurrence and recency of occurrence of the words in the text.
Claim 4
Dependent Claim
53 words
A dictionary memory, comprising: means for storing a degree of association between words; means for storing information on occurrence of words in a text; and means for determining a degree of activity of a word based on information on the frequency of occurrence and recency of occurrence of the words in the text.
Claim 5
Dependent Claim
21 words
A dictionary memory according to claim 2, wherein a word that occurred more recently is assigned a higher degree of activity.
Claim 6
Dependent Claim
60 words
A dictionary memory according to claim 2, wherein the degree of association between words represents a possibility that the words co-occur in a text, and wherein the dictionary memory includes means for adjusting the degree of association between a word that occurred in a text and another word based on the degree of activity of another word at that point.
Claim 7
Dependent Claim
34 words
A dictionary memory according to claim 2, wherein the dictionary memory includes means for determining likelihood for a word based on the degrees of association between words and the degrees of activity of words.
Claim 8
Dependent Claim
56 words
A dictionary memory according to claim 2, wherein the dictionary memory includes means for inputting words that are candidates for occurrence in a text, means for determining a likelihood for each candidate based on the degrees of association between words and the degrees of activity of words, and means for outputting the likelihood for each candidate.
Claim 9
Dependent Claim
63 words
A dictionary memory according to claim 2, wherein the dictionary memory includes means for inputting words that are candidates for occurrence in a text together with the respective likelihood thereof, means for revising the likelihood for each candidate based on the degrees of association between words and the degrees of activity of words, and means for outputting the revised likelihood for each candidate.
Claim 10
Dependent Claim
68 words
A dictionary memory according to claim 2, wherein the dictionary memory includes means for inputting words that are candidates for occurrence in a text, means for determining a likelihood for each candidate based on the degrees of association between words and the degrees of activity of words and selecting a word that has the maximum likelihood, and means for outputting the selected word that has the maximum likelihood.
Claim 11
Dependent Claim
74 words
A dictionary memory according to claim 2, wherein the dictionary memory includes means for inputting words that are candidates for occurrence in a text together with the respective likelihood thereof, means for revising the likelihood for each candidate based on the degrees of association between words and the degrees of activity of words and selecting a word that has the maximum likelihood, and means for outputting the selected word that has the maximum likelihood.
References Cited (Backward Citations)
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2000-07-28 | 2001-01-27 | 2001-07-29 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2004-07-28 | 2005-01-27 | 2005-07-29 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2008-07-28 | 2009-01-27 | 2009-07-29 | $7700.00 | Window Closed / Lapsed |