%0 Conference Paper %1 1220221 %A Gorman, James %A Curran, James R. %B ACL-44: Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the Association for Computational Linguistics %C Morristown, NJ, USA %D 2006 %I Association for Computational Linguistics %K similarity %P 361--368 %R http://dx.doi.org/10.3115/1220175.1220221 %T Scaling distributional similarity to large corpora %U http://portal.acm.org/citation.cfm?id=1220175.1220221&coll=GUIDE&dl=ACM&CFID=14547294&CFTOKEN=67134592 %X Accurately representing synonymy using distributional similarity requires large volumes of data to reliably represent infrequent words. However, the naïve nearest-neighbour approach to comparing context vectors extracted from large corpora scales poorly (O(n2) in the vocabulary size).In this paper, we compare several existing approaches to approximating the nearest-neighbour search for distributional similarity. We investigate the trade-off between efficiency and accuracy, and find that SASH (Houle and Sakuma, 2005) provides the best balance.

@inproceedings{1220221, abstract = {Accurately representing synonymy using distributional similarity requires large volumes of data to reliably represent infrequent words. However, the naïve nearest-neighbour approach to comparing context vectors extracted from large corpora scales poorly (O(n2) in the vocabulary size).In this paper, we compare several existing approaches to approximating the nearest-neighbour search for distributional similarity. We investigate the trade-off between efficiency and accuracy, and find that SASH (Houle and Sakuma, 2005) provides the best balance.}, added-at = {2008-12-09T23:36:11.000+0100}, address = {Morristown, NJ, USA}, author = {Gorman, James and Curran, James R.}, biburl = {https://www.bibsonomy.org/bibtex/2b3cac6faeb3e9f6363d263a0affc5808/jamesh}, booktitle = {ACL-44: Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the Association for Computational Linguistics}, description = {Scaling distributional similarity to large corpora}, doi = {http://dx.doi.org/10.3115/1220175.1220221}, interhash = {a9bddd9d18cfbe2af544662837718ceb}, intrahash = {b3cac6faeb3e9f6363d263a0affc5808}, keywords = {similarity}, location = {Sydney, Australia}, pages = {361--368}, publisher = {Association for Computational Linguistics}, timestamp = {2008-12-09T23:36:11.000+0100}, title = {Scaling distributional similarity to large corpora}, url = {http://portal.acm.org/citation.cfm?id=1220175.1220221&coll=GUIDE&dl=ACM&CFID=14547294&CFTOKEN=67134592}, year = 2006 }