Syllable Word Segmentation for Mandarin Chinese via Double Ranking of the Left and Right Context
博士 === 國立清華大學 === 資訊工程學系 === 100 === Syllable word segmentations as a part of Chinese phonetic input methods (CPIM) involve more overlapping boundaries than word segmentations because of homophone ambiguities. A CPIM usually assumes that the input is a complete sentence, and evaluates the performanc...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | en_US |
Published: |
2012
|
Online Access: | http://ndltd.ncl.edu.tw/handle/70825467974900378132 |
id |
ndltd-TW-100NTHU5392070 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-100NTHU53920702015-10-13T21:27:24Z http://ndltd.ncl.edu.tw/handle/70825467974900378132 Syllable Word Segmentation for Mandarin Chinese via Double Ranking of the Left and Right Context Jiang, Tian-Jian 姜天戩 博士 國立清華大學 資訊工程學系 100 Syllable word segmentations as a part of Chinese phonetic input methods (CPIM) involve more overlapping boundaries than word segmentations because of homophone ambiguities. A CPIM usually assumes that the input is a complete sentence, and evaluates the performance based on a well-formed corpus. However, most Pinyin users prefer progressive text entry in short chunks, mainly in one or two words each, which is even more popular on handheld devices with limited computing power. Short chunks do not provide enough contexts to perform the best possible syllable-to-character conversion, especially when a chunk consists of overlapping boundaries. Those overlapping ambiguities show directional tendencies. This dissertation proposes a double ranking (DR) strategy on the left and right context. Experiments show that DR has the benefits of less memory with competitive performance compared to the frequency-based method (low memory and fast) and the conditional random fields model (larger memory and slower). 許聞廉 2012 學位論文 ; thesis 65 en_US |
collection |
NDLTD |
language |
en_US |
format |
Others
|
sources |
NDLTD |
description |
博士 === 國立清華大學 === 資訊工程學系 === 100 === Syllable word segmentations as a part of Chinese phonetic input methods (CPIM) involve more overlapping boundaries than word segmentations because of homophone ambiguities. A CPIM usually assumes that the input is a complete sentence, and evaluates the performance based on a well-formed corpus. However, most Pinyin users prefer progressive text entry in short chunks, mainly in one or two words each, which is even more popular on handheld devices with limited computing power. Short chunks do not provide enough contexts to perform the best possible syllable-to-character conversion, especially when a chunk consists of overlapping boundaries. Those overlapping ambiguities show directional tendencies. This dissertation proposes a double ranking (DR) strategy on the left and right context. Experiments show that DR has the benefits of less memory with competitive performance compared to the frequency-based method (low memory and fast) and the conditional random fields model (larger memory and slower).
|
author2 |
許聞廉 |
author_facet |
許聞廉 Jiang, Tian-Jian 姜天戩 |
author |
Jiang, Tian-Jian 姜天戩 |
spellingShingle |
Jiang, Tian-Jian 姜天戩 Syllable Word Segmentation for Mandarin Chinese via Double Ranking of the Left and Right Context |
author_sort |
Jiang, Tian-Jian |
title |
Syllable Word Segmentation for Mandarin Chinese via Double Ranking of the Left and Right Context |
title_short |
Syllable Word Segmentation for Mandarin Chinese via Double Ranking of the Left and Right Context |
title_full |
Syllable Word Segmentation for Mandarin Chinese via Double Ranking of the Left and Right Context |
title_fullStr |
Syllable Word Segmentation for Mandarin Chinese via Double Ranking of the Left and Right Context |
title_full_unstemmed |
Syllable Word Segmentation for Mandarin Chinese via Double Ranking of the Left and Right Context |
title_sort |
syllable word segmentation for mandarin chinese via double ranking of the left and right context |
publishDate |
2012 |
url |
http://ndltd.ncl.edu.tw/handle/70825467974900378132 |
work_keys_str_mv |
AT jiangtianjian syllablewordsegmentationformandarinchineseviadoublerankingoftheleftandrightcontext AT jiāngtiānjiǎn syllablewordsegmentationformandarinchineseviadoublerankingoftheleftandrightcontext |
_version_ |
1718062682809040896 |