Abstract | ||
---|---|---|
Treebanks are not large enough to reliably model precise lexical phenomena. This deficiency provokes attachment errors in the parsers trained on such data. We propose in this paper to compute lexical affinities, on large corpora, for specific lexico-syntactic configurations that are hard to disambiguate and introduce the new information in a parser. Experiments on the French Treebank showed a relative decrease of the error rate of 7.1% Labeled Accuracy Score yielding the best parsing results on this treebank. |
Year | Venue | Keywords |
---|---|---|
2012 | ACL | deficiency provokes attachment error,lexical affinity,relative decrease,error rate,parsing result,new information,french treebank,model precise lexical phenomenon,labeled accuracy score,large corpus,semi-supervised dependency |
Field | DocType | Volume |
Computer science,Word error rate,Speech recognition,Dependency grammar,Natural language processing,Treebank,Artificial intelligence,Parsing,Affinities | Conference | P12-1 |
Citations | PageRank | References |
4 | 0.41 | 23 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Seyed Abolghasem Mirroshandel | 1 | 73 | 13.23 |
Alexis Nasr | 2 | 182 | 33.91 |
Joseph Le Roux | 3 | 175 | 16.34 |