Adding semantic information: unsupervised clusters for coreference resolution
Iris Hendrickx, Walter M. P. Daelemans · 2007
We evaluate the effect of automatically generated semantic clusters as as information source in our machine learning approach to the task of coreference resolution for Dutch. We compare these clusters which group semantically similar nouns together, to two semantic features based on WordNet encoding synonym and hypernym relations between nouns. Our experiments with two learners show that the cluster-based features lead to a small improvement for memory-based learning, while combining both leads to an improvement for maximum entropy modeling. 1.