Computer Laboratory

Diarmuid Ó Séaghdha

Co-occurrence contexts for noun compound interpretation

Diarmuid Ó Séaghdha and Ann Copestake, ACL-07 Workshop on A Broader Perspective on Multiword Expressions

PDF (slightly revised version)

Contextual information extracted from corpora is frequently used to model semantic similarity. We discuss distinct classes of context types and compare their effectiveness for compound noun interpretation. Contexts corresponding to word-word similarity perform better than contexts corresponding to relation similarity, even when relational co-occurrences are extracted from a much larger corpus. Combining word-similarity and relation-similarity kernels further improves SVM classification performance.

@inproceedings{OSeaghdha:Copestake:07,
	title = {Co-occurrence Contexts for Noun Compound Interpretation},
	author = {Diarmuid {\'O S\'eaghdha} and Ann Copestake},
	booktitle = {Proceedings of the ACL-07 Workshop on A Broader Perspective on Multiword Expressions},
	address = {Prague, Czech Republic},
	year = {2007},
}