论文信息 - A Complete Wn1.5 to Wn1.6 Mapping

A Complete Wn1.5 to Wn1.6 Mapping

We describe a robust approach for linking already existing lexical/semantic hierarchies. We use a constraint satisfaction algorithm (relaxation labelling) to select {among a set of candidates{ the node in a target taxonomy that bests matches each node in a source taxonomy. In this paper we present the complete mapping of the nominal, verbal, adjectival and adverbial parts of WordNet 1.5 onto WordNet 1.6.

L. Padr

[1] Horacio Rodríguez,et al. Automatically extracting Translation Links using a wide coverage semantic taxonomy , 2007 .

[2] Lluís Padró,et al. A Hybrid Environment for Syntax-Semantic Tagging , 1998, ArXiv.

[3] Lluís Padró,et al. Mapping Multilingual Hierarchies Using Relaxation Labeling , 1999, EMNLP.

[4] Carme Torras. Relaxation and Neural Learning: Points of Convergence and Divergence , 1989, J. Parallel Distributed Comput..

[5] Horacio Rodríguez,et al. Using WordNet for Building WordNets , 1998, WordNet@ACL/COLING.

[6] Eduard H. Hovy,et al. Building Japanese-English Dictionary based on Ontology for Machine Translation , 1994, HLT.

[7] Lluís Padró,et al. Developing a hybrid NP parser , 1997, ANLP.

[8] Horacio Rodríguez,et al. Combining Multiple Methods for the Automatic Construction of Multilingual WordNets , 1997, ArXiv.

[9] Lluís Padró,et al. A Flexible POS Tagger Using an Automatically Acquired Language Model , 1997, ACL.

[10] Lluís Padró,et al. Mapping WordNets Using Structural Information , 2000, ACL.

[11] Kevin Knight,et al. Building a Large-Scale Knowledge Base for Machine Translation , 1994, AAAI.