Please use this identifier to cite or link to this item:
https://scholarbank.nus.edu.sg/handle/10635/35850
Title: | 现代汉语词语搭配自动抽取研究 = Study on Modern Chinese Collocation Automatic Extracting | Authors: | 秦少康 QIN SHAOKANG |
Keywords: | collocation, automatic extracting, sense, language learning, sense-tagged corpus, learner’s dictionary | Issue Date: | 6-Jan-2012 | Citation: | 秦少康, QIN SHAOKANG (2012-01-06). 现代汉语词语搭配自动抽取研究 = Study on Modern Chinese Collocation Automatic Extracting. ScholarBank@NUS Repository. | Abstract: | The thesis holds that two characteristics of word combination are critical for judging collocation from a free word combination and idiom: 1) some words could not become a collocate of a node although they might have the same relationship with the node as the collocates, 2) the meaning of the collocation is transparent. Based on a large-scale sense-tagged corpus, the thesis provides an improved extracting method, which could extract sense information of the node and collocate. After many tests, the thesis takes the view that using different parameters for words of different part of speech and different occurrences is of great help in extracting collocations. By this way, the thesis reports nearly the same result as those systems based on word form. | URI: | http://scholarbank.nus.edu.sg/handle/10635/35850 |
Appears in Collections: | Ph.D Theses (Open) |
Show full item record
Files in This Item:
File | Description | Size | Format | Access Settings | Version | |
---|---|---|---|---|---|---|
QinSK.pdf | 5.21 MB | Adobe PDF | OPEN | None | View/Download | |
QinSK-Cover1.pdf | 225.61 kB | Adobe PDF | OPEN | None | View/Download | |
QinSK-Cover2.pdf | 64.31 kB | Adobe PDF | OPEN | None | View/Download |
Google ScholarTM
Check
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.