D09-1128 SC classifier into our ME based coreference resolution system . This section examines how our
C04-1033 compared the performance of difierent coreference resolution systems . The flrst line summarizes the
C04-1033 Evaluation 4.1 Data collection Our coreference resolution system is a component of our information
A00-1020 the major drawbacks of existing coreference resolution systems is their inability to recognize
D09-1102 information to improve learning-based coreference resolution systems . He used an anaphoricity classifier
A00-1020 best-performing and most robust coreference resolution systems employ knowledge-based techniques
D09-1128 performance . The best reported ACE2 coreference resolution system ( Ng , 2007a ; Ng , 2007b ) has
A00-2024 corporation for licensing us the coreference resolution system . This material is based upon
D09-1102 information can be incorporated into a coreference resolution system . Experiments show that their
A00-1020 pat - terns . Even though other coreference resolution systems perform better for some specific
D08-1068 challenging , and unsupervised coreference resolution systems are still rare to this date .
D09-1128 features can boost our baseline coreference resolution system by 10.4 % and 9.7 % using MUC
D12-1045 Abstract We introduce a novel coreference resolution system that models entities and events
D09-1128 knowledge that has been employed in coreference resolution system is the semantic class ( SC )
D08-1068 introduces the first unsupervised coreference resolution system that is as accurate as supervised
D09-1128 Versley for his support with BART coreference resolution system and the three anonymous reviewers
A00-1020 of a data-driven multilingual coreference resolution system , we prepared a corpus of Romanian
D09-1128 incorporate semantic knowledge into coreference resolution systems : different knowledge sources
C04-1075 strategies . <title> A High-Performance Coreference Resolution System using a Constraint-based Multi-Agent
D09-1128 coreference sys - tems ) , our coreference resolution system can obtain an increase of 10.4
hide detail