Skip N-gram modeling for Near-Synonym choice
碩士 === 元智大學 === 資訊管理學系 === 100 === Near-synonym is not only an important thing in natural language applications, and also very important for the second language learner. Although, near-synonym represent a groups of words with similar meaning. But, in specific case and specific usage, we choice the w...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Online Access: | http://ndltd.ncl.edu.tw/handle/49303465739107534247 |
id |
ndltd-TW-100YZU05396060 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-100YZU053960602015-10-13T21:33:10Z http://ndltd.ncl.edu.tw/handle/49303465739107534247 Skip N-gram modeling for Near-Synonym choice 應用跳脫語言模型於同義詞取代之研究 Shih-Ting Chen 陳士婷 碩士 元智大學 資訊管理學系 100 Near-synonym is not only an important thing in natural language applications, and also very important for the second language learner. Although, near-synonym represent a groups of words with similar meaning. But, in specific case and specific usage, we choice the wrong near-synonym may cause wrong meaning, even cause grammatical errors. Therefore, we hope system can use contextual information to differentiate near-synonym. So far, there are many studies about near-synonym, the methods of these studies include: PMI and N-gram modeling. We want to use different method to improve the accuracy, so we use Skip N-gram modeling for near-synonym choice in SemEval-2007 task, the results show that our proposed method is feasible and the accuracy have improved significantly Liang-ChihYu 禹良治 學位論文 ; thesis 35 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 元智大學 === 資訊管理學系 === 100 === Near-synonym is not only an important thing in natural language applications, and also very important for the second language learner. Although, near-synonym represent a groups of words with similar meaning. But, in specific case and specific usage, we choice the wrong near-synonym may cause wrong meaning, even cause grammatical errors. Therefore, we hope system can use contextual information to differentiate near-synonym.
So far, there are many studies about near-synonym, the methods of these studies include: PMI and N-gram modeling. We want to use different method to improve the accuracy, so we use Skip N-gram modeling for near-synonym choice in SemEval-2007 task, the results show that our proposed method is feasible and the accuracy have improved significantly
|
author2 |
Liang-ChihYu |
author_facet |
Liang-ChihYu Shih-Ting Chen 陳士婷 |
author |
Shih-Ting Chen 陳士婷 |
spellingShingle |
Shih-Ting Chen 陳士婷 Skip N-gram modeling for Near-Synonym choice |
author_sort |
Shih-Ting Chen |
title |
Skip N-gram modeling for Near-Synonym choice |
title_short |
Skip N-gram modeling for Near-Synonym choice |
title_full |
Skip N-gram modeling for Near-Synonym choice |
title_fullStr |
Skip N-gram modeling for Near-Synonym choice |
title_full_unstemmed |
Skip N-gram modeling for Near-Synonym choice |
title_sort |
skip n-gram modeling for near-synonym choice |
url |
http://ndltd.ncl.edu.tw/handle/49303465739107534247 |
work_keys_str_mv |
AT shihtingchen skipngrammodelingfornearsynonymchoice AT chénshìtíng skipngrammodelingfornearsynonymchoice AT shihtingchen yīngyòngtiàotuōyǔyánmóxíngyútóngyìcíqǔdàizhīyánjiū AT chénshìtíng yīngyòngtiàotuōyǔyánmóxíngyútóngyìcíqǔdàizhīyánjiū |
_version_ |
1718066335044337664 |