Publikace na Matematicko-fyzikální fakulta |
2012
Abstrakt
The possibility of deleting a word from a sentence without violating its syntactic correctness belongs to traditionally known manifes tations of syntactic dependency. We introduce a novel unsupervised parsing approach that is based on a new n-gram reducibility measure.
We perform experiments across 18 languages available in CoNLL data and we show that our approach achieves better accuracy for the majority of the languages then previously reported results.