Upper Bound for Cross-Lingual Concept Mapping with External Translation Resources

被引：0

作者：

Abu Helou, Mamoun ^{[1
]}

Palmonari, Matteo ^{[1
]}

机构：

[1] Univ Milano Bicocca, Milan, Italy

来源：

NATURAL LANGUAGE PROCESSING AND INFORMATION SYSTEMS, NLDB 2015 | 2015年 / 9103卷

关键词：

Cross-lingual linking; Word Nets; Machine translation; Web-based lexicons;

D O I：

10.1007/978-3-319-19581-0_41

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

One way to achieve semantic interoperability when data lexicalized in different languages is by means of cross-lingual linking. Translation resources are used as an intermediate step to reduce the language barriers. The key challenge is to select the correct mapping among candidate matches. We define an experiment to study upper bounds for the correctness of a cross-lingual ontology matching system. We highlight different lexical characteristics that can support the selection step. We believe that our findings can be useful in the design of cross-lingual mapping algorithms.

引用

页码：424 / 431

页数：8

共 25 条

[11] Collaboratively built semi-structured content and Artificial Intelligence: The story so far [J].