Easy Victories and Uphill Battles in Coreference Resolution

Abstract

Classical coreference systems encode various syntactic, discourse, and semantic phenomena explicitly, using heterogenous features computed from hand-crafted heuristics. In contrast , we present a state-of-the-art coreference system that captures such phenomena implicitly , with a small number of homogeneous feature templates examining shallow properties of mentions. Surprisingly, our features are actually more effective than the corresponding hand-engineered ones at modeling these key linguistic phenomena, allowing us to win " easy victories " without crafted heuris-tics. These features are successful on syntax and discourse; however, they do not model semantic compatibility well, nor do we see gains from experiments with shallow semantic features from the literature, suggesting that this approach to semantics is an " uphill battle. " Nonetheless, our final system 1 outper-forms the Stanford system (Lee et al. (2011), the winner of the CoNLL 2011 shared task) by 3.5% absolute on the CoNLL metric and outperforms the IMS system (Björkelund and Farkas (2012), the best publicly available En-glish coreference system) by 1.9% absolute.

Extracted Key Phrases

10 Figures and Tables

Showing 1-10 of 37 references

English Gigaword Third Edition. Linguistic Data Consortium, Catalog Number LDC2007T07

  • David Graff, Junbo Kong, Ke Chen, Kazuaki Maeda
  • 2007
Highly Influential
3 Excerpts
Showing 1-10 of 74 extracted citations
0204020132014201520162017
Citations per Year

96 Citations

Semantic Scholar estimates that this publication has received between 74 and 132 citations based on the available data.

See our FAQ for additional information.