US5826220A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Translation word learning scheme for machine translation
Assignee: Toshiba Corp
•
Filing: 1995-10-02
•
Granted: 1998-10-20
•
Expires: 2015-10-02
Abstract
Abstract A translation word learning scheme for a machine translation capable of learning translation words for each lexical rule separately and easily. In this scheme, a translation word for each original word is obtained by a machine translation using a translation dictionary storing headwords in the first language, a plurality of lexical rules for each headword, and at least one candidate translation word in the second language corresponding to each lexical rule. Then, a change of a translation word from that obtained by the machine translation to another translation word specified by a user is learned by registering a learning data indicating a headword, a top candidate translation word corresponding to a lexical rule applied in translating this headword, and the specified translation word. This specified translation word is used in subsequent translations only when an original word and a top candidate translation word for this original word obtained by the machine translation coincide with the headword and the top candidate translation word indicated in the learning data.
Inventors
- 👤 Kimihito Takeda
- 👤 Yoshimi Saito
- 👤 Hideki Hirakawa
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-01 19:14
CPC Classifications
G; G06; G06F; G06F40/00; G06F40/20; G06F40/268; G06F40/279; G06F40/284; G06F40/40; G06F40/55
Claims Analysis
Total Claims: 12
Claim 1
Independent Claim
193 words
A method of machine translation, comprising the steps of: translating original sentences in a first language into translated sentences in a second language, by obtaining a translation word for each original word according to a translation dictionary storing headwords in the first language, a plurality of lexical rules for each headword, and at least one candidate translation word in the second language corresponding to each lexical rule; and learning a change of a translation word for one headword from a top candidate translation word obtained at the translating step according to one lexical rule in the translation dictionary to another translation word specified by a user, by registering a learning data indicating said one headword, the top candidate translation word corresponding to said one lexical rule, and said another translation word as a learned translation word, such that said another translation word is used in subsequent translations as a translation word for an original word coinciding with said one headword only when a top candidate translation word obtained at the translating step according to the lexical rules in the translation dictionary coincides with the top candidate translation word indicated in the learning data.
Claim 2
Independent Claim
193 words
A method of machine translation, comprising the steps of: translating original sentences in a first language into translated sentences in a second language, by obtaining a translation word for each original word according to a translation dictionary storing headwords in the first language, a plurality of lexical rules for each headword, and at least one candidate translation word in the second language corresponding to each lexical rule; and learning a change of a translation word for one headword from a top candidate translation word obtained at the translating step according to one lexical rule in the translation dictionary to another translation word specified by a user, by registering a learning data indicating said one headword, the top candidate translation word corresponding to said one lexical rule, and said another translation word as a learned translation word, such that said another translation word is used in subsequent translations as a translation word for an original word coinciding with said one headword only when a top candidate translation word obtained at the translating step according to the lexical rules in the translation dictionary coincides with the top candidate translation word indicated in the learning data.
Claim 3
Dependent Claim
69 words
The method of claim 1, wherein said another translation word is specified by the user by presenting a list of candidate translation words for a case of translating said one headword according to said one lexical rule, allowing a user to select an appropriate translation word from the list of candidate translation words, and registering the selected candidate translation word as said another translation word in the learning data.
Claim 4
Dependent Claim
40 words
The method of claim 1, wherein said another translation word is specified by the user by allowing the user to enter a desired translation word, and registering the entered translation word as said another translation word in the learning data.
Claim 5
Dependent Claim
68 words
The method of claim 1, wherein the learning step registers the learning data by replacing a previously learned translation word by said another translation word in a learning dictionary in the case that the learning dictionary has an already existing learning data indicating said one headword and the top candidate translation word corresponding to said one lexical rule when said another translation word is specified by the user.
Claim 6
Dependent Claim
63 words
The method of claim 1, wherein the learning step registers the learning data by adding the learning data in a learning dictionary in the case that the learning dictionary does not have an already existing learning data indicating said one headword and the top candidate translation word corresponding to said one lexical rule when said another translation word is specified by the user.
Claim 7
Dependent Claim
193 words
A machine translation system, comprising: means for translating original sentences in a first language into translated sentences in a second language, by obtaining a translation word for each original word according to a translation dictionary storing headwords in the first language, a plurality of lexical rules for each headword, and at least one candidate translation word in the second language corresponding to each lexical rule; and means for learning a change of a translation word for one headword from a top candidate translation word obtained by the translating means according to one lexical rule in the translation dictionary to another translation word specified by a user, by registering a learning data indicating said one headword, the top candidate translation word corresponding to said one lexical rule, and said another translation word as a learned translation word, such that said another translation word is used in subsequent translations as a translation word for an original word coinciding with said one headword only when a top candidate translation word obtained by the translating means according to the lexical rules in the translation dictionary coincides with the top candidate translation word indicated in the learning data.
Claim 8
Dependent Claim
193 words
A machine translation system, comprising: means for translating original sentences in a first language into translated sentences in a second language, by obtaining a translation word for each original word according to a translation dictionary storing headwords in the first language, a plurality of lexical rules for each headword, and at least one candidate translation word in the second language corresponding to each lexical rule; and means for learning a change of a translation word for one headword from a top candidate translation word obtained by the translating means according to one lexical rule in the translation dictionary to another translation word specified by a user, by registering a learning data indicating said one headword, the top candidate translation word corresponding to said one lexical rule, and said another translation word as a learned translation word, such that said another translation word is used in subsequent translations as a translation word for an original word coinciding with said one headword only when a top candidate translation word obtained by the translating means according to the lexical rules in the translation dictionary coincides with the top candidate translation word indicated in the learning data.
Claim 9
Dependent Claim
65 words
The system of claim 6, further comprising: means for presenting a list of candidate translation words for a case of translating said one headword according to said one lexical rule; and means for allowing the user to select an appropriate translation word from the list of candidate translation words, and registering the selected candidate translation word as said another translation word in the learning data.
Claim 10
Dependent Claim
33 words
The system of claim 6, further comprising: means for allowing the user to enter a desired translation word, and registering the entered translation word as said another translation word in the learning data.
Claim 11
Dependent Claim
68 words
The system of claim 6, wherein the learning means registers the learning data by replacing a previously learned translation word by said another translation word in a learning dictionary in the case that the learning dictionary has an already existing learning data indicating said one headword and the top candidate translation word corresponding to said one lexical rule when said another translation word is specified by the user.
Claim 12
Dependent Claim
63 words
The system of claim 6, wherein the learning means registers the learning data by adding the learning data in a learning dictionary in the case that the learning dictionary does not have an already existing learning data indicating said one headword and the top candidate translation word corresponding to said one lexical rule when said another translation word is specified by the user.
References Cited (Backward Citations)
US4502128A
Cited
US5010486A
Cited
US4980829A
Cited
US5181163A
Cited
US5214583A
Cited
US5311429A
Cited
US5329446A
Cited
US5442547A
Cited
US5373441A
Cited
US5373442A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2001-10-19 | 2002-04-20 | 2002-10-20 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2005-10-19 | 2006-04-20 | 2006-10-20 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2009-10-19 | 2010-04-20 | 2010-10-20 | $7700.00 | Window Closed / Lapsed |