J05-3004 describe our first case study for antecedent selection in other-anaphora . 4.1 Corpus
J05-3004 approach in the following way for antecedent selection . Step 1 : Relation Identification
J05-3004 anaphoricity determination in addition to antecedent selection . Additionally , future work
D14-1222 joint inference framework for antecedent selection by exploring Markov logic networks
D14-1222 report an accuracy of 0.41 for antecedent selection given gold bridging anaphora
J05-3004 additional lexical information for antecedent selection . Thus , in Example ( 8 ) , for
J05-3004 recently used in Web search for antecedent selection for bridging anaphora by Poesio
E14-3006 antecedent . Their experiments focus on antecedent selection only , assuming that the recognition
J05-3004 WordNet as a knowledge source for antecedent selection in other-anaphora resolution
D08-1069 able to capitalize on the better antecedent selection capabilities offered by the ranking
J05-3004 constructed lexical hierarchies in antecedent selection ? And is the use of the Web an
J01-4002 best antecedent candidates . 3 . Antecedent selection : Consider anaphors a in the
D13-1077 separate bridging recognition and antecedent selection . One could argue that a joint
J05-3004 lexical knowledge for the task of antecedent selection or antecedent ranking in anaphora
J05-3004 obtaining lexical knowledge for antecedent selection in other-anaphora and definite
J05-3004 distractors . 5.3 WordNet for Antecedent Selection in Definite NP Coreference We
J05-3004 , as we restrict our study to antecedent selection for the NPs that are marked in
J05-3004 Anaphora Types Using the Web for antecedent selection in anaphora resolution is novel
C96-2158 the binding restrictions in the antecedent selection stet ) . To avoid that ( te.sirable
C04-1033 coreferential to NPj . In our study , two antecedent selection strategies , Most Recent First
hide detail