Abstract | ||
---|---|---|
This paper compares a number of recently proposed models for computing context sensitive word similarity. We clarify the connections between these models, simplify their formulation and evaluate them in a unified setting. We show that the models are essentially equivalent if syntactic information is ignored, and that the substantial performance differences previously reported disappear to a large extent when these simplified variants are evaluated under identical conditions. Furthermore, our reformulation allows for the design of a straightforward and fast implementation. |
Year | Venue | Keywords |
---|---|---|
2012 | HLT-NAACL | word meaning,syntactic information,substantial performance difference,fast implementation,large extent,unified setting,context sensitive word similarity,identical condition |
Field | DocType | Citations |
Computer science,Natural language processing,Artificial intelligence,Syntax | Conference | 8 |
PageRank | References | Authors |
0.56 | 11 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Georgiana Dinu | 1 | 510 | 33.36 |
Stefan Thater | 2 | 756 | 38.54 |
Sören Laue | 3 | 114 | 11.79 |