Method and apparatus for automated language translation

• US 5,884,247 A
• Filed: 10/31/1996
• Issued: 03/16/1999
• Est. Priority Date: 10/31/1996
• Status: Expired due to Fees

• Current Assignee: Wordstream
• Original Assignee: Dialect Corporation
• Inventors: Christy, Sam
• Primary Examiner(s): Thomas, Joseph
• Application Number:
  US08/740,654
• Time in Patent Office: 866 Days
• Field of Search: 704/1, 704/2, 704/3, 704/4, 704/5, 704/7, 704/9, 704/10, 704/277, 395/12
• US Class Current: 704/7
• CPC Class Codes: G06F 40/55 Rule-based translation

Abstract

Language translation is accomplished by representing natural-language sentences in accordance with a constrained grammar and vocabulary structured to permit direct substitution of linguistic units in one language for corresponding linguistic units in another language. Preferably, the vocabulary is represented in a series of physically or logically distinct databases, each containing entries representing a form class as defined in the grammar. Translation involves direct lookup between the entries of a reference sentence and the corresponding entries in one or more target languages.

Claims

1. A method of translating information from a first language into a second language, the method comprising:

a. providing reference and target sets of nominal, connector, and descriptor databases in reference and target languages, each nominal database comprising a series of nominal entries, each connector database comprising a series of connector entries each specifying a relationship between at least two nominal terms, and each descriptor database comprising a series of descriptor entries describing nominal entries, the entries of the reference set of databases corresponding to the entries of the target set of databases;

b. generating a sentence in the reference language from a plurality of entries from the reference set of databases according to rules defining a constrained grammar;

c. addressing the target set of databases with the reference entries to retrieve target entries corresponding thereto; and

d. translating the sentence by directly substituting the reference entries with the target entries.

2. The method of claim 1 further comprising the step of providing logical-connector databases in reference and target languages, each logical-connector database comprising a series of entries establishing sets.

3. The method of claim 2 wherein the sentence is generated by selecting an item from the nominal database and expanding the sentence by applying at least one of the rules:

a. to a nominal entry, add a descriptor entry from the descriptor database;

b. to a nominal entry, add a connector entry from the connector database and another nominal entry from the nominal database;

c. to a nominal entry, add a logical connector from the logical-connector database and another nominal entry from the nominal database; and

d. to a descriptor entry, add a logical-connector entry from the logical-connector database and another descriptor entry from the descriptor database.

4. The method of claim 2 wherein the logical-connector database comprises the entries and, or.

5. The method of claim 1 wherein the nominal entries name a person, place, thing, activity or idea.

6. The method of claim 5 wherein the nominal entries include the terms set forth in Table 2.

7. The method of claim 1 wherein the connector entries show action, being or state of being.

8. The method of claim 7 wherein the connector entries include the terms set forth in Table 3.

9. The method of claim 1 wherein the descriptor entries describe a quality, quantity, state or type of a nominal entry.

10. The method of claim 5 wherein the descriptor entries include the entries set forth in Table 4.

11. Apparatus for translating information from a first language into a second language, the apparatus comprising:

a. first database means comprising a series of nominal entries in a reference and at least one target language;

b. second database means comprising a series of connector entries in a reference and at least one target language, the connector entries each specifying a relationship between at least two nominal entries;

c. third database means comprising a series of descriptor entries in a reference and at least one target language, the descriptor entries describing nominal entries;

d. means for accepting an input in the reference language, the input comprising entries from the database means organized in accordance with rules defining a constrained grammar; and

e. analysis means for (i) addressing the target set of databases with the input to retrieve target entries corresponding thereto and (ii) translating the sentence by directly substituting the target entries for the input.

12. The apparatus of claim 11 further comprising fourth database means comprising a series of entries establishing sets.

13. The apparatus of claim 12 wherein the analysis means is configured to ensure that the input conforms to a sentence constructed in accordance with expansion rules comprising:

a. to a nominal entry, add a descriptor entry from the third database means;

b. to a nominal entry, add a connector entry from the second database means and another nominal entry from the first database means;

c. to a nominal entry, add an entry from the fourth database means and another nominal entry from the first database; and

d. to a descriptor entry, add an entry from the fourth database and another descriptor entry from the third database.

14. The apparatus of claim 12 wherein the fourth database means comprises the entries and, or.

15. The apparatus of claim 11 wherein the nominal entries name a person, place, thing, activity or idea.

16. The apparatus of claim 15 wherein the first database means includes the terms set forth in Table 2.

17. The apparatus of claim 11 wherein the connector entries show action, being or state of being.

18. The apparatus of claim 17 wherein the second database means includes the terms set forth in Table 3.

19. The apparatus of claim 11 wherein the descriptor entries describe a quality, quantity, state or type of a nominal entry.

20. The apparatus of claim 19 wherein the third database means includes the terms set forth in Table 4.

21. The apparatus of claim 11 further comprising a thesaurus for identifying, for an input term not matching any of the database entries, a database entry closest in meaning to the input term.

22. The apparatus of claim 11 further comprising means for displaying the translation.