Abstract | 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. |
Conclusion | In this paper, we have demonstrated the utility of association information for coreference resolution . |
Introduction | Coreference resolution (CoRe) is the process of finding markables (noun phrases) referring to the same real world entity or concept. |
Introduction | Our experiments are conducted using the MCORE system (“Modular COreference REsolution” ).1 MCORE can operate in three different settings: unsupervised (subsystem A-INF), supervised (subsystem SUCRE (Kobdani and Schutze, 2010)), and self-trained (subsystem UNSEL). |
Introduction | SUCRE (“SUpervised Coreference REsolution” ) is trained on a labeled corpus (manually or automatically labeled) similar to standard CoRe systems. |
Related Work | (2002) used co-training for coreference resolution , a semi-supervised method. |
System Architecture | We take a self-training approach to coreference resolution : We first label the corpus using the unsupervised model A-INF and then train the supervised model SUCRE on this automatically labeled training corpus. |
Introduction | The felicitousness of zero anaphoric reference depends on the referred entity being sufficiently salient, hence this type of data—particularly in Japanese and Italian—played a key role in early work in coreference resolution , e.g., in the development of Centering (Kameyama, 1985; Walker et a1., 1994; Di Eugenio, 1998). |
Introduction | We integrate the zero anaphora resolver with a coreference resolver and demonstrate that the approach leads to improved results for both Italian and Japanese. |
Introduction | In Section 5 we discuss experiments testing that adding our zero anaphora detector and resolver to a full coreference resolver would result in overall increase in performance. |
Prior Work | Concept discovery is also related to coreference resolution (Ng, 2008; Poon and Domingos, 2008). |
Prior Work | The difference between the two problems is that coreference resolution finds noun phrases that refer to the same concept within a specific document. |
Prior Work | We think the concepts produced by a system like ConceptResolver could be used to improve coreference resolution by providing prior knowledge about noun phrases that can refer to the same concept. |