Automatic interpretation of noun compounds using wordnet similarity
IJCNLP'05 Proceedings of the Second international joint conference on Natural Language Processing
Using lexical and relational similarity to classify semantic relations
EACL '09 Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics
| Hi-index | 0.00 |
The ability to correctly interpret and produce noun-noun compounds such as WIND FARM or CARBON TAX is an important part of the acquisition of language in various domains of discourse. One approach to the interpretation of noun-noun compounds assumes that people make use of distributional information about how the constituent words of compounds tend to combine; another assumes that people make use of information about the two constituent concepts' features to produce interpretations. We present an experiment that examines how people acquire both the distributional information and conceptual information relevant to compound interpretation. A plausible model of the interpretation process is also presented.