Unsupervised clustering of morphologically related Chinese words

政大機構典藏 > 理學院 > 資訊科學系 > 會議論文 > Item 140.119/98226

Please use this identifier to cite or link to this item: http://nccur.lib.nccu.edu.tw/handle/140.119/98226

Title:	Unsupervised clustering of morphologically related Chinese words
Authors:	Lee, Chia-Ling;Chang, Ya-Ning;Liu, Chao-Lin;Lee, Chia-Ying;Hsu, Jane Yung-jen 劉昭麟
Contributors:	資科系
Keywords:	morphological awareness;human cognition;computational linguistics;Chinese character meaning
Date:	2014-07
Issue Date:	2016-06-22 16:21:48 (UTC+8)
Abstract:	Many linguists consider morphological awareness a major factor that affects children’s reading development. A Chinese character embedded in different compound words may carry related but different meanings. For example, “商店(store)”, “商品(commodity)”, “商代(Shang Dynasty)”, and “商朝(Shang Dynasty)” can form two clusters: {“商店”, “商品”} and {“商代”, “商朝”}. In this paper, we aim at unsupervised clustering of a given family of morphologically related Chinese words. Successfully differentiating these words can contribute to both computer assisted Chinese learning and natural language understanding. In Experiment 1, we employed linguistic factors at the word, syntactic, semantic, and contextual levels in aggregated computational linguistics methods to handle the clustering task. In Experiment 2, we recruited adults and children to perform the clustering task. Experimental results indicate that our computational model achieved the same level of performance as children.
Relation:	Proceedings of the Thirty-Sixth Annual Meeting of the Cognitive Science Society (COGSCI'14), 2543‒2548. Québec City, Québec, Canada, 23-26 July 2014
Data Type:	conference
Appears in Collections:	[資訊科學系] 會議論文

Files in This Item:

File	Description	Size	Format
2543-2548.pdf		534Kb	Adobe PDF	270	View/Open

社群 sharing

Loading...