节点文献
A New Multiword Expression Metric and Its Applications
【摘要】 <正>Multiword Expressions(MWEs) appear frequently and ungrammatically in natural languages.Identifying MWEs in free texts is a very challenging problem.This paper proposes a knowledge-free,unsupervised,and language-independent Multiword Expression Distance(MED).The new metric is derived from an accepted physical principle,measures the distance from an n-gram to its semantics,and outperforms other state-of-the-art methods on MWEs in two applications: question answering and named entity extraction.
【Abstract】 Multiword Expressions(MWEs) appear frequently and ungrammatically in natural languages.Identifying MWEs in free texts is a very challenging problem.This paper proposes a knowledge-free,unsupervised,and language-independent Multiword Expression Distance(MED).The new metric is derived from an accepted physical principle,measures the distance from an n-gram to its semantics,and outperforms other state-of-the-art methods on MWEs in two applications: question answering and named entity extraction.
【Key words】 multiword expressions; information distance; question answering; named entity extraction;
- 【文献出处】 Journal of Computer Science & Technology ,计算机科学技术学报(英文版) , 编辑部邮箱 ,2011年01期
- 【分类号】TP391.1
- 【被引频次】4
- 【下载频次】75