When added to a state-of-the-art coreference baseline, our Web features give significant gains on multiple datasets (ACE 2004 and ACE 2005) and metrics (MUC and B3), resulting in the best results reported to date for the end-to-end task of coreference resolution.

There is also work on end-to-end coreference resolution that uses large noun-similarity lists (Daumé III and Marcu, 2005) or structured knowledge bases such as Wikipedia (Yang and Su, 2007; Haghighi and Klein, 2009; Kobdani et al., 2011) and YAGO (Rahman and Ng, 2011).

Altogether, our final system produces the best numbers reported to date on end-to-end coreference resolution (with automatically detected system mentions) on multiple data sets (ACE 2004 and ACE 2005) and metrics (MUC and B3), achieving significant improvements over the Reconcile DT baseline and over the state-of-the-art results of Haghighi and Klein (2010).

datasets for end-to-end coreference resolution (see Section 4.3).

Finally, the third task is to complete the end-to-end navigation task.

Finally, we evaluate the system on the end-to-end navigation task.

Table 4: End-to-end navigation task completion rates.

5.4 End-to-End Result

We compare their influence on RankingSVM accuracy, alignment crossing-link number, end-to-end BLEU score, and the model size.

These features also correspond to BLEU score improvement for End-to-End evaluations.