Abstract | ||
---|---|---|
This paper describes our system for the Semeval 2012 Sentence Textual Similarity task. The system is based on a combination of few simple vector space-based methods for word meaning similarity. Evaluation results show that a simple combination of these unsupervised data-driven methods can be quite successful. The simple vector space components achieve high performance on short sentences; on longer, more complex sentences, they are outperformed by a surprisingly competitive word overlap baseline, but they still bring improvements over this baseline when incorporated into a mixture model. |
Year | Venue | Keywords |
---|---|---|
2012 | SemEval@NAACL-HLT | vector-based model,simple vector,evaluation result,complex sentence,competitive word,simple combination,sentence textual similarity task,high performance,mixture model,simple vector space component,semantic textual similarity,word meaning similarity |
Field | DocType | Citations |
Vector space,SemEval,Computer science,Artificial intelligence,Natural language processing,Sentence,Mixture model | Conference | 3 |
PageRank | References | Authors |
0.38 | 8 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Georgiana Dinu | 1 | 510 | 33.36 |
Stefan Thater | 2 | 756 | 38.54 |