Patent US5850561A successfully refreshed from Google Patents.
US5850561A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Glossary construction tool
Assignee: Alcatel Lucent SAS
•
Filing: 1994-09-23
•
Granted: 1998-12-15
•
Expires: 2014-09-23
Abstract
Abstract A glossary construction tool for generating and maintaining a translation glossary, consisting of a number of terms and their translations. The glossary construction tool includes a terminology list development tool for generating a terminology list in the source language and a glossary development tool for automatically obtaining candidate translations for the terms in the terminology list. The terminology list development tool will construct the terminology list in the source language by analyzing the source text document to be translated and automatically extracting a list of candidate terms, comprised of multiple word noun phrases and single words not appearing on a standard or predefined stop list of "noise" words. The glossary development tool will obtain candidate translations for terms in the final terminology list by searching the source text document of a word-aligned text pair for a term to be translated and then provide candidate translations based on the indicated alignment with the target text document of the aligned text pair. A concordance tool provides monolingual and bilingual concordances in order to facilitate the user's evaluation of the automatically generated list of candidate terms and candidate translations, respectively.
Inventors
- 👤 Kenneth Ward Church
- 👤 Ido Dagan
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-01 16:20
CPC Classifications
G; G06; G06F; G06F40/00; G06F40/20; G06F40/237; G06F40/247
Claims Analysis
Total Claims: 43
Claim 1
Independent Claim
83 words
A system for compiling a terminology list from a source document, said system comprising: a processor for extracting multiple word noun phrases from said source document; a predefined stop list stored in a memory; means for extracting single words not appearing on the predefined stop list from said source document; and a display for presenting said extracted multiple word noun phrases and said single words in a candidate terminology list to a user for evaluation in order to develop a final terminology list.
Claim 2
Independent Claim
83 words
A system for compiling a terminology list from a source document, said system comprising: a processor for extracting multiple word noun phrases from said source document; a predefined stop list stored in a memory; means for extracting single words not appearing on the predefined stop list from said source document; and a display for presenting said extracted multiple word noun phrases and said single words in a candidate terminology list to a user for evaluation in order to develop a final terminology list.
Claim 3
Dependent Claim
28 words
The system of claim 1, further comprising a part-of-speech tagger for analyzing said source document and identifying the part of speech for each word in said source document.
Claim 4
Dependent Claim
65 words
The system of claim 1, wherein said display includes a first window and a second window and wherein said system further comprises: means for displaying said candidate terminology list in said first window; means for selecting one of said terms in said candidate terminology list; and a concordance tool for displaying each occurrence of said selected term in said source document in said second window.
Claim 5
Dependent Claim
45 words
The system of claim 3, further comprising means for selecting one of said occurrences of said selected term presented in said second window and wherein said display further includes a third window for displaying the full context of said selected occurrence of said selected term.
Claim 6
Dependent Claim
38 words
The system of claim 3, wherein said concordance tool further comprises processing means for sorting each of said occurrences of said selected term such that all occurrences of identical preceding contexts of said selected term are grouped together.
Claim 7
Dependent Claim
19 words
The system of claim 3, further including means for adding a selected candidate term to said final terminology list.
Claim 8
Dependent Claim
19 words
The system of claim 3, further including means for deleting a selected candidate term from said candidate terminology list.
Claim 9
Dependent Claim
21 words
The system of claim 1, further comprising processing means for sorting said candidate terminology list for efficient presentation to said user.
Claim 10
Dependent Claim
19 words
The system of claim 8, wherein linguistically related terms in said sorted candidate terminology list appear near one another.
Claim 11
Independent Claim
64 words
A system for automatically compiling a terminology list from a source document, said system comprising: a predefined stop list stored in a memory; a processor for extracting multiple word noun phrases and single words not appearing on the predefined stop list from said source document; and means for compiling said terminology list comprised of said extracted multiple word noun phrases and said single words.
Claim 12
Independent Claim
64 words
A system for automatically compiling a terminology list from a source document, said system comprising: a predefined stop list stored in a memory; a processor for extracting multiple word noun phrases and single words not appearing on the predefined stop list from said source document; and means for compiling said terminology list comprised of said extracted multiple word noun phrases and said single words.
Claim 13
Dependent Claim
28 words
The system of claim 10, further comprising a part-of-speech tagger for analyzing said source document and identifying the part of speech for each word in said source document.
Claim 14
Dependent Claim
73 words
The system of claim 10, further comprising a display for presenting said terminology list and wherein said display includes a first window and a second window and wherein said system further comprises: means for displaying said terminology list in said first window; means for selecting one of said terms in said terminology list; and a concordance tool for displaying each occurrence of said selected term in said source document in said second window.
Claim 15
Dependent Claim
45 words
The system of claim 12, further comprising means for selecting one of said occurrences of said selected term presented in said second window and wherein said display further includes a third window for displaying the full context of said selected occurrence of said selected term.
Claim 16
Dependent Claim
38 words
The system of claim 12, wherein said concordance tool further comprises processing means for sorting each of said occurrences of said selected term such that all occurrences of identical preceding contexts of said selected term are grouped together.
Claim 17
Dependent Claim
17 words
The system of claim 12, further including means for adding a selected term to said terminology list.
Claim 18
Dependent Claim
17 words
The system of claim 12, further including means for deleting a selected term from said terminology list.
Claim 19
Dependent Claim
20 words
The system of claim 10, further comprising processing means for sorting said terminology list for efficient presentation to a user.
Claim 20
Dependent Claim
18 words
The system of claim 17, wherein linguistically related terms in said sorted terminology list appear near one another.
Claim 21
Independent Claim
116 words
A system for automatically generating one or more candidate translations for a source language term to be translated into a target language, said system comprising: a memory storing a previously translated source language document and a target language document which is a translation of said source language document; a word level text alignment tool for automatically aligning said pair of previously translated documents; and a processor for searching for said term to be translated in said source language document and obtaining a candidate translation based on the indicated alignment of the words of said term to be translated in the source language document with the words of the target language document of the aligned text pair.
Claim 22
Independent Claim
116 words
A system for automatically generating one or more candidate translations for a source language term to be translated into a target language, said system comprising: a memory storing a previously translated source language document and a target language document which is a translation of said source language document; a word level text alignment tool for automatically aligning said pair of previously translated documents; and a processor for searching for said term to be translated in said source language document and obtaining a candidate translation based on the indicated alignment of the words of said term to be translated in the source language document with the words of the target language document of the aligned text pair.
Claim 23
Dependent Claim
40 words
The system of claim 19, wherein said word level text alignment tool provides a mapping of the words in said source language document with the words of the corresponding translation in the target language document of said aligned text pair.
Claim 24
Dependent Claim
49 words
The system of claim 19, wherein said candidate translations are obtained by extracting the sequence of words spanning between the first and last words in said target language document of the aligned pair that are aligned with any words of the selected source term in said source language document.
Claim 25
Dependent Claim
64 words
The system of claim 19, further comprising: a display; means for presenting said candidate translation on said display for evaluation by a user; and a bilingual concordance tool for presenting on said display each occurrence of a source term and the corresponding candidate translation in the source language document of the aligned text pair and the target language document of the aligned text pair.
Claim 26
Dependent Claim
24 words
The system of claim 22, further including means for adding said term to be translated and a selected candidate translation to a translation glossary.
Claim 27
Dependent Claim
37 words
The system of claim 22, further comprising means for selecting a bilingual concordance line and for presenting the full text of said source language document and said translated target language document corresponding to said selected bilingual concordance.
Claim 28
Dependent Claim
29 words
The system of claim 24, wherein said presentation of said full text of said source language document and said translated target language document are in a dual scroll mode.
Claim 29
Independent Claim
81 words
A method for compiling a terminology list from a source document, said method comprising the steps of: extracting multiple word noun phrases from said source document; storing a predefined stop list in a memory; extracting single words not appearing on the predefined stop list from said source document; and presenting said extracted multiple word noun phrases and said single words in a candidate terminology list on a display to a user for evaluation in order to develop a final terminology list.
Claim 30
Independent Claim
81 words
A method for compiling a terminology list from a source document, said method comprising the steps of: extracting multiple word noun phrases from said source document; storing a predefined stop list in a memory; extracting single words not appearing on the predefined stop list from said source document; and presenting said extracted multiple word noun phrases and said single words in a candidate terminology list on a display to a user for evaluation in order to develop a final terminology list.
Claim 31
Dependent Claim
22 words
The method of claim 26, further comprising the step of identifying the part of speech for each word in said source document.
Claim 32
Dependent Claim
60 words
The method of claim 26, wherein said display includes a first window and a second window and wherein said method further comprises the steps of: displaying said candidate terminology list in said first window; selecting one of said terms in said candidate terminology list; and displaying each occurrence of said selected term in said source document in said second window.
Claim 33
Dependent Claim
38 words
The method of claim 28, wherein said displaying step further comprises the step of sorting each of said occurrences of said selected term such that all occurrences of identical preceding contexts of said selected term are grouped together.
Claim 34
Dependent Claim
20 words
The method of claim 28, further including the step of adding a selected candidate term to said final terminology list.
Claim 35
Dependent Claim
20 words
The method of claim 28, further including the step of deleting a selected candidate term from said candidate terminology list.
Claim 36
Dependent Claim
21 words
The method of claim 26, further comprising the step of sorting said candidate terminology list for efficient presentation to said user.
Claim 37
Dependent Claim
19 words
The method of claim 32, wherein linguistically related terms in said sorted candidate terminology list appear near one another.
Claim 38
Independent Claim
114 words
A method for automatically generating one or more candidate translations for a source language term to be translated into a target language, said method comprising the steps of: storing a previously translated source language document and a target language document which is a translation of said source language document in a memory; automatically aligning said pair of previously translated documents at the word level; and searching for said term to be translated in said source language document and obtaining a candidate translation based on the indicated alignment of the words of said term to be translated in the source language document with the words of the target language document of the aligned text pair.
Claim 39
Independent Claim
114 words
A method for automatically generating one or more candidate translations for a source language term to be translated into a target language, said method comprising the steps of: storing a previously translated source language document and a target language document which is a translation of said source language document in a memory; automatically aligning said pair of previously translated documents at the word level; and searching for said term to be translated in said source language document and obtaining a candidate translation based on the indicated alignment of the words of said term to be translated in the source language document with the words of the target language document of the aligned text pair.
Claim 40
Dependent Claim
42 words
The method of claim 34, wherein said step of aligning said pair of documents provides a mapping of the words in said source language document with the words of the corresponding translation in the target language document of said aligned text pair.
Claim 41
Dependent Claim
53 words
The method of claim 34, wherein said step of obtaining candidate translations comprises the step of extracting the sequence of words spanning between the first and last words in said target language document of the aligned pair that are aligned with any words of the selected source term in said source language document.
Claim 42
Dependent Claim
58 words
The method of claim 34, further comprising the steps of: presenting said candidate translation on a display for evaluation by a user; and presenting on said display each occurrence of a source term and the corresponding candidate translation in the source language document of the aligned text pair and the target language document of the aligned text pair.
Claim 43
Dependent Claim
25 words
The method of claim 37, further including the step of adding said term to be translated and a selected candidate translation to a translation glossary.
References Cited (Backward Citations)
US5551049A
Cited
US5146405A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2001-12-14 | 2002-06-15 | 2002-12-15 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2005-12-14 | 2006-06-15 | 2006-12-15 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2009-12-14 | 2010-06-15 | 2010-12-15 | $7700.00 | Window Closed / Lapsed |