Abstract | ||
---|---|---|
We propose a novel unsupervised approach for distinguishing literal and non-literal use of idiomatic expressions. Our model combines an unsupervised and a supervised classifier. The former bases its decision on the cohesive structure of the context and labels training data for the latter, which can then take a larger feature space into account. We show that a combination of both classifiers leads to significant improvements over using the unsupervised classifier alone. |
Year | Venue | Keywords |
---|---|---|
2009 | EMNLP | classifier combination,cohesive structure,novel unsupervised approach,labels training data,former base,unsupervised classifier,contextual idiom detection,labelled data,larger feature space,supervised classifier,non-literal use,significant improvement,idiomatic expression,feature space |
Field | DocType | Volume |
Training set,Feature vector,Pattern recognition,Expression (mathematics),Computer science,Speech recognition,Artificial intelligence,Classifier (linguistics),Margin classifier,Linear classifier,Machine learning | Conference | D09-1 |
Citations | PageRank | References |
13 | 1.00 | 8 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Linlin Li | 1 | 117 | 7.66 |
Caroline Sporleder | 2 | 453 | 31.84 |