P06-1079 relations in a given discourse , zero-anaphora resolution , is essential in a wide range
P09-1073 Previous work Early methods for zero-anaphora resolution were developed with rule-based
P09-1073 machine learning-based approach to zero-anaphora resolution searches for an antecedent in
P06-1079 semantic processing . Recent work on zero-anaphora resolution can be located in two different
P09-1073 Walker ( 1996 ) to the task of zero-anaphora resolution . We propose a machine learning-based
P06-1079 the proposed model on overall zero-anaphora resolution including inter-sentential cases
J08-3002 their work ) to perform Japanese zero-anaphora resolution . They utilized the same linear
P09-1073 Section 2 , the procedure for zero-anaphora resolution can be decomposed into two subtasks
P09-1073 Section 2 presents the task of zero-anaphora resolution and then Section 3 gives an overview
P09-1073 unspecified in the context . The task of zero-anaphora resolution can be decomposed into two subtasks
P06-1079 quotations . 5.4 Impact on overall zero-anaphora resolution We next evaluated the effects
P06-1079 different research contexts . First , zero-anaphora resolution is studied in the context of
P06-1079 Conclusion In intra-sentential zero-anaphora resolution , syntactic patterns of the appearance
P06-1079 well also in intra-sentential zero-anaphora resolution . We hope this finding to be
P06-1079 model and the inter-sentential zero-anaphora resolution in the SCM using structural information
P06-1079 Matsumoto Abstract We approach the zero-anaphora resolution problem by decomposing it into
P06-1079 parsing , a model specialized for zero-anaphora resolution needs to be devised on the top
P06-1079 remarkably well for intra-sentential zero-anaphora resolution . Futhermore , SCM STR is significantly
P06-1079 improves the overall performance of zero-anaphora resolution . In our next step , we are going
P06-1079 decomposition We approach the zero-anaphora resolution problem by decomposing it into
hide detail