An Analysis of Tree Topological Features in Classifier-Based Unlexicalized Parsing
Refereed conference paper presented and published in conference proceedings


香港中文大学研究人员 ( 现职)

张钦良教授 (语言学及现代语言系)

庄华祥先生 (决策科学与企业经济学系)

陈伟光教授 (决策科学与企业经济学系)

全文

没有全文档案提供

引用次数
Web of Sciencehttp://aims.cuhk.edu.hk/converis/portal/Publication/1WOS source URL

其它资讯

摘要A novel set of "tree topological features" (TTFs) is investigated for improving a classifier-based unlexicalized parser. The features capture the location and shape of subtrees in the treebank. Four main categories of TTFs are proposed and compared. Experimental results showed that each of the four categories independently improved the parsing accuracy significantly over the baseline model. When combined using the ensemble technique, the best unlexicalized parser achieves 84% accuracy without any extra language resources, and matches the performance of early lexicalized parsers. Linguistically. TTFs approximate linguistic notions such as grammatical weight, branching property and structural parallelism. This is illustrated by studying how the features capture structural parallelism in processing coordinate structures.

着者Chan SWK, Chong MWC, Cheung LYL
会议名称http://aims.cuhk.edu.hk/converis/portal/Publication/12th Annual Conference on Intelligent Text Processing and Computational Linguistics
会议开始日20.02.20http://aims.cuhk.edu.hk/converis/portal/Publication/1http://aims.cuhk.edu.hk/converis/portal/Publication/1
会议完结日26.02.20http://aims.cuhk.edu.hk/converis/portal/Publication/1http://aims.cuhk.edu.hk/converis/portal/Publication/1
会议地点Tokyo
会议国家日本
期刊名称Lecture Notes in Computer Science
出版年份20http://aims.cuhk.edu.hk/converis/portal/Publication/1http://aims.cuhk.edu.hk/converis/portal/Publication/1
月份http://aims.cuhk.edu.hk/converis/portal/Publication/1
日期http://aims.cuhk.edu.hk/converis/portal/Publication/1
卷号6608
出版社SPRINGER-VERLAG BERLIN
页次http://aims.cuhk.edu.hk/converis/portal/Publication/155 - http://aims.cuhk.edu.hk/converis/portal/Publication/170
国际标準书号978-3-642-http://aims.cuhk.edu.hk/converis/portal/Publication/19399-6
国际标準期刊号0302-9743
语言英式英语

关键词machine learning; parsing; topological features; unlexicalized model
Web of Science 学科类别Computer Science; Computer Science, Artificial Intelligence; Computer Science, Interdisciplinary Applications; Computer Science, Theory & Methods