BibSonomy :: bibtex  ::

tag user group author concept BibTeX key search:all search:seandalai
A blue social bookmark and publication sharing system.
tags · relations · groups · popular
help · blog · about
login · register
seandalai's BibTeX entry:  

Semantic Labeling of Compound Nominalization in Chinese

Proceedings of the ACL Workshop A Broader Perspective on Multiword Expressions, 2007.
Authors: Jinglei Zhao and Hui Liu and Ruzhan Lu
URL: http://www.let.uu.nl/~Nicole.Gregoire/personal/ACL07-MWE/pdf/ACL07-MWE10.pdf
Tags: 2007 chinese compounds nominalisation workshop
Abstract: This paper discusses the semantic interpretation of compound nominalizations in Chinese. We propose four coarse-grained semantic roles of the noun modifier and use a Maximum Entropy Model to label such relations in a compound nominalization. The feature functions used for the model are web-based statistics acquired via role related paraphrase patterns, which are formed by a set of word instances of prepositions, support verbs, feature nouns and aspect markers. By applying a sub-linear transformation and discretization of the raw statistics, a rate of approximately 77% is obtained for classification of the four semantic relations.
| URL | BibTeX  
@inproceedings{Zhao:EtAl:07,
title = {Semantic Labeling of Compound Nominalization in Chinese},
author = {Jinglei Zhao and Hui Liu and Ruzhan Lu},
booktitle = {Proceedings of the ACL Workshop A Broader Perspective on Multiword Expressions},
url = {http://www.let.uu.nl/~Nicole.Gregoire/personal/ACL07-MWE/pdf/ACL07-MWE10.pdf},
year = {2007},
abstract = {This paper discusses the semantic interpretation of compound nominalizations in Chinese. We propose four coarse-grained semantic roles of the noun modifier and use a Maximum Entropy Model to label such relations in a compound nominalization. The feature functions used for the model are web-based statistics acquired via role related paraphrase patterns, which are formed by a set of word instances of prepositions, support verbs, feature nouns and aspect markers. By applying a sub-linear transformation and discretization of the raw statistics, a rate of approximately 77% is obtained for classification of the four semantic relations.},
keywords = {2007 chinese compounds nominalisation workshop }
}