论文信息 - Hybrid Approach for Coreference Resolution

Hybrid Approach for Coreference Resolution

This paper describes our participation in the CoNLL-2011 shared task for closed task. The approach used combines refined salience measure based pronominal resolution and CRFs for non-pronominal resolution. In this work we also use machine learning based approach for identifying non-anaphoric pronouns.

Sobha Lalitha Devi | Pattabhi R. K. Rao | R. Vijay Sundar Ram | C. S. Malarkodi | A. Akilandeswari

[1] Nianwen Xue,et al. CoNLL-2011 Shared Task: Modeling Unrestricted Coreference in OntoNotes , 2011, CoNLL Shared Task.

[2] Hwee Tou Ng,et al. A Machine Learning Approach to Coreference Resolution of Noun Phrases , 2001, CL.

[3] Sameer Pradhan,et al. Unrestricted Coreference: Identifying Entities and Events in OntoNotes , 2007, International Conference on Semantic Computing (ICSC 2007).

[4] L. Sobha. Anaphora Resolution Using Named Entity and Ontology , 2008 .

[5] Dekang Lin,et al. Bootstrapping Path-Based Pronoun Resolution , 2006, ACL.

[6] Andrew McCallum,et al. Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data , 2001, ICML.

[7] Shalom Lappin,et al. An Algorithm for Pronominal Anaphora Resolution , 1994, CL.