Cross-linguistic Attribute Selection for REG: Comparing Dutch and English

In this paper we describe a cross-linguistic experiment in attribute selection for referring expression generation. We used a graph-based attribute selection algorithm that was trained and cross-evaluated on English and Dutch data. The results indicate that attribute selection can be done in a largely language independent way.

• Type: Journal
• Year: 2010
• Where: INLG
• Authors: Mariët Theune, Ruud Koolen, Emiel Krahmer
• Keywords: Attribute Selection, Graph-based Attribute Selection, INLG 2010, Language Independent Way, Natural Language Processing