Paper: Post-Retrieval Clustering Using Third-Order Similarity Measures

ACL ID P13-2028
Title Post-Retrieval Clustering Using Third-Order Similarity Measures
Venue Annual Meeting of the Association of Computational Linguistics
Session Short Paper
Year 2013
Authors

Post-retrieval clustering is the task of clus- tering Web search results. Within this context, we propose a new methodology that adapts the classical K-means algo- rithm to a third-order similarity measure initially developed for NLP tasks. Results obtained with the definition of a new stop- ping criterion over the ODP-239 and the MORESQUE gold standard datasets evi- dence that our proposal outperforms all re- ported text-based approaches.