Modeling the level of involvement of verbal arguments

DOI10.1007/3-540-44686-9_3MaRDI QIDQ2763087zbMATH OpenFDO

Authors Leo Ferres

Publication date 14 January 2002

Published in Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL http://link.springer.de/link/service/series/0558/bibs/2004/20040032

Mathematics Subject Classification ID

Natural language processing (68T50) Computing methodologies and applications (68U99)

Review text

The purpose of this paper is to discuss the output of a neural network based on a linguistic model for recognizing the levels of involvement of different verbal arguments, assuming the non-discreteness of thematic relations and their non-primitiveness in linguistic theory. The network's output called for hypothesizing that, contrary to the received view, there is no equal level of involvement in verbal arguments, one having to be always more invovolved than the others, even when having the same number of Proto-Agent and Proto-Patients contributing properties. For the entire collection see [Zbl 0976.68583].

Recommendations

• Deriving syntactic properties of arguments and adjuncts from neo-Davidsonian semantics
• scientific article; zbMATH DE number 1746152
• scientific article; zbMATH DE number 1292572
• Optimality: from neural networks to universal grammar
• scientific article; zbMATH DE number 2079780

This page was built for publication: Modeling the level of involvement of verbal arguments

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2763087)