METHOD FOR CONSTRUCTING CHINESE DICTIONARY AND APPARATUS AND STORAGE MEDIA USING THE SAME

• US 20100138217A1
• Filed: 06/01/2009
• Published: 06/03/2010
• Est. Priority Date: 11/28/2008
• Status: Active Grant

• Current Assignee: Institute For Information Industry
• Original Assignee: Institute For Information Industry
• Inventors: Wu, Chien-Cheng, Chen, Yu-Ru, Chang, Jason S., Ku, Tsun, Wang, Wen-Nan, Hsieh, Wen-Tai
• Granted Patent: US 8,346,541 B2
• Time in Patent Office: Days
• US Class Current: 704/10
• CPC Class Codes: G06F 40/242 Dictionaries
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: G06F 40/53 Processing of non-Latin text kana-to-kanji conversion G06F40/129; vowelisation G06F40/232

Abstract

A method for constructing a Chinese dictionary is disclosed, including determining a probability for nominalization of a Chinese term with a given collocation term according to a determination rule and the correlation between the Chinese term and its corresponding collocations, wherein the Chinese term is determined to be a verb part-of-speech. The method further includes modifying the verb part-of-speech of the Chinese term with the given collocation term to an appropriate part-of-speech when the probability for nominalization of the Chinese term with the given collocation term is higher than a predetermined value, and storing the correlation between the Chinese term, the given collocation term and the appropriate part-of-speech in a storage device.

Claims

1. A method for constructing a Chinese dictionary, comprising:

determining a probability for nominalization of a Chinese term with a given collocation term according to a determination rule and the correlation between the Chinese term and its corresponding collocations, wherein the Chinese term is determined to be a verb part-of-speech;

modifying the verb part-of-speech of the Chinese term with the given collocation term to an appropriate part-of-speech when the probability for nominalization of the Chinese term with the given collocation term is higher than a predetermined value; and

storing the correlation between the Chinese term, the given collocation term and the appropriate part-of-speech in a storage device.

2. The method for constructing a Chinese dictionary as claimed in claim 1, further comprising determining at least a Chinese collocation of the Chinese term according to the appropriate part-of-speech and the correlation between the Chinese term and its collocations.

3. The method for constructing a Chinese dictionary as claimed in claim 2, further comprising storing the Chinese collocation in a database.

4. The method for constructing a Chinese dictionary as claimed in claim 2, further comprising providing a plurality of Chinese sentences and determining the Chinese collocation according to the number of Chinese characters located between the Chinese term and the Chinese collocation in each of a plurality of Chinese sentences.

5. The method for constructing a Chinese dictionary as claimed in claim 2, further comprising providing a plurality of Chinese sentences and determining the Chinese collocation according to the number of sentences among a plurality of Chinese sentences that comprise both the Chinese term and the Chinese collocation.

6. The method for constructing a Chinese dictionary as claimed in claim 4, further comprising determining the Chinese collocation according to the number of sentences among the Chinese sentences that contain both the Chinese term and the Chinese collocation.

7. The method for constructing a Chinese dictionary as claimed in claim 1, further comprising collecting at least a Chinese sentence, wherein the Chinese sentence in order comprises a Chinese pre-term, the Chinese term and a Chinese post-term, and the part-of-speech for the Chinese pre-term and the Chinese post-term are respectively determined.

8. The method for constructing a Chinese dictionary as claimed in claim 7, further comprising determining the probability for nominalization according to the Chinese pre-term, the Chinese term, the Chinese post-term, the determined part-of-speech for the Chinese pre-term, the determined verb part-of-speech for the Chinese term and the determined part-of-speech for the Chinese post-term.

9. An apparatus for constructing a Chinese dictionary, comprising:

a nominalization determination module determining a probability for nominalization of a Chinese term with a given collocation term according to a determination rule and the correlation between the Chinese term and its corresponding collocations, wherein the Chinese term is determined to be a verb part-of-speech; and

a part-of-speech modification module modifying the verb part-of-speech of the Chinese term with the given collocation term to an appropriate part-of-speech when the probability for nominalization of the Chinese term with the given collocation term is higher than a predetermined value.

10. The apparatus for constructing a Chinese dictionary as claimed in claim 9, further comprising a collocation generation module determining at least a Chinese collocation of the Chinese term according to the appropriate part-of-speech and the correlation between the Chinese term and its collocations.

11. The apparatus for constructing a Chinese dictionary as claimed in claim 10, further comprising a database storing the Chinese collocation.

12. The apparatus for constructing a Chinese dictionary as claimed in claim 10, wherein the collocation generation module determines the Chinese collocation according to the number of Chinese characters located between the Chinese term and the Chinese collocation in each of a plurality of Chinese sentences.

13. The apparatus for constructing a Chinese dictionary as claimed in claim 10, wherein the collocation generation module determines the Chinese collocation according to the number of sentences among a plurality of Chinese sentences that comprise both the Chinese term and the Chinese collocation.

14. The apparatus for constructing a Chinese dictionary as claimed in claim 12, wherein the collocation generation module determines the Chinese collocation according to the number of sentences among the plurality of Chinese sentences that comprise both the Chinese term and the Chinese collocation.

15. The apparatus for constructing a Chinese dictionary as claimed in claim 9, further comprising an article collection module collecting at least a Chinese sentence, wherein the Chinese sentence in order comprises a Chinese pre-term, the Chinese term and a Chinese post-term, and the part-of-speech of the Chinese pre-term and the Chinese post-term are respectively determined.

16. The apparatus for constructing a Chinese dictionary as claimed in claim 15, wherein the nominalization determination module determines the probability for nominalization according to the Chinese pre-term, the Chinese term, the Chinese post-term, the determined part-of-speech for the Chinese pre-term, the determined verb part-of-speech for the Chinese term and the determined part-of-speech for the Chinese post-term.

17. A storage medium for storing a program for constructing a Chinese dictionary, wherein the program for constructing the Chinese dictionary comprises a plurality of program codes to be loaded onto a computer system so that a method for constructing the Chinese dictionary is executed by the computer system, and the method comprises:

determining a probability for nominalization of a Chinese term with a given collocation term according to a determination rule and the correlation between the Chinese term and its corresponding collocations, wherein the Chinese term is determined to be a verb part-of-speech;

modifying the verb part-of-speech to an appropriate part-of-speech of the Chinese term with the given collocation term when the probability for nominalization of the Chinese term with the given collocation term is higher than a predetermined value; and

storing the correlation between the Chinese term, the given collocation term, and the appropriate part-of-speech in a storage device.

18. The storage medium as claimed in claim 17, wherein the method further comprises determining at least a Chinese collocation for the Chinese term according to the appropriate part-of-speech and the correlation between the Chinese term and its collocations.

19. The storage medium as claimed in claim 18, wherein the method further comprises determining the Chinese collocation according to the number of Chinese characters located between the Chinese term and the Chinese collocation in each of a plurality of Chinese sentences.

20. The storage medium as claimed in claim 18, wherein the method further comprises determining the Chinese collocation according to the number of sentences among a plurality of Chinese sentences that comprise both the Chinese term and the Chinese collocation.