Bootstrapping coreference resolution using word associations
Hamidreza Kobdani, Hinrich Schuetze, Michael Schiehlen, Hans Kamp · Meeting of the Association for Computational Linguistics · 2011
In this paper, we present an unsupervised framework that bootstraps a complete coreference resolution (CoRe) system from word associations mined from a large unlabeled corpus. We show that word associations are useful for CoRe -- e.g., the strong association between Obama and President is an indicator of likely coreference. Association information has so far not been used in CoRe because it is sparse and difficult to learn from small labeled corpora. Since unlabeled text is readily available, our unsupervised approach addresses the sparseness problem. In a self-training framework, we train a decision tree on a corpus that is automatically labeled using word associations. We show that this unsupervised system has better CoRe performance than other learning approaches that do not use manually labeled data.