This paper reports on the annotation of a corpus of 1 million words with four semantic annotation layers, including named entities, coreference relations, semantic roles and spati...
Extending a machine learning based coreference resolution system with a feature capturing automatically generated information about semantic roles improves its performance.
There have been considerable attempts to incorporate semantic knowledge into coreference resolution systems: different knowledge sources such as WordNet and Wikipedia have been us...
Zhiheng Huang, Guangping Zeng, Weiqun Xu, Asli &Cc...
Of the ten million words of contemporary standard Dutch in the Spoken Dutch Corpus (Corpus Gesproken Nederlands, CGN), a selection of one million words of natural spoken language ...
Heleen Hoekstra, Michael Moortgat, Ineke Schuurman...
This paper proposes a method to resolve Japanese zero pronouns by identifying their antecedents. Our method uses a probabilistic model, which is decomposed into syntactic and sema...