Abstract. In this paper, we present a new ontology-based formalism for representing patent information. The framework defines concepts and relations for the major aspects of paten...
Mark Giereth, Steffen Koch, Yiannis Kompatsiaris, ...
or untagged treebanks. ' When trained on an untagged This paper presents a method for constructing deterministic Prolog parsers from corpora of parsed sentences. Our approach ...
arrhythmias (extended abstract) Elisa Fromont, Ren´e Quiniou, Marie-Odile Cordier We are interested in using parallel universes to learn interpretable models that can be subseque...
A central issue in logical concept induction is the prospect of inconsistency. This problem may arise due to noise in the training data, or because the target concept does not fit...
We present a new approach to learning a semantic parser (a system that maps natural language sentences into logical form). Unlike previous methods, it exploits an existing syntact...