| W02-1008 | outperforms the best-performing | learning-based coreference system | to date . 1 Introduction Noun |
| N09-1065 | baseline . Our first baseline is the | learning-based coreference system | described in Section 2 , which |
| P04-1020 | anaphoricity information for improving | learning-based coreference systems | : representation and optimization |
| N09-1065 | follows . Section 2 describes our | learning-based coreference system | . In Section 3 , we give an overview |
| P04-1020 | anaphoricity information to improve | learning-based coreference systems | . In par - ticular , we present |
| P04-1020 | of our experiments , we use our | learning-based coreference system | ( Ng and Cardie , 2002b ) . Features |
| P04-1020 | their effectiveness in improving a | learning-based coreference system | . Extensive experiments on the |
| P05-1020 | choices will be guided by previous | learning-based coreference systems | , as described below . Training |
| N09-1065 | their effectiveness in improving a | learning-based coreference system | on the ACE data sets . 1 Introduction |
| P07-1068 | to improve the performance of a | learning-based coreference system | , and ( 2 ) employing SC knowledge |
| D09-1101 | been employed by state-of-the-art | learning-based coreference systems | ( e.g. , Soon et al. ( 2001 ) |
| P05-1020 | describes how we select these | learning-based coreference systems | and acquire the ranking model |
| P04-1020 | anaphoricity information can be used by a | learning-based coreference system | either as hard bypassing constraints |
| P05-1020 | Selecting Coreference Systems A | learning-based coreference system | can be defined by four elements |
| N09-1065 | their effectiveness in improving a | learning-based coreference system | . To our knowledge , there has |
| P05-1020 | data-driven approaches , yielding | learning-based coreference systems | that rival their hand-crafted |
