HOTCoref

The IMS HOTCoref system is a data-driven coreference resolution system that models coreference within a document as a directed rooted tree

HOTCoref

Type
Tool
Author
Anders Björkelund
Description

The IMS HOTCoref system is a data-driven coreference resolution system [0]. It models coreference within a document as a directed rooted tree. For learning it adopts the idea of latent antecedents and exploits the tree structure for the purpose of non-local (with respect to a single pair of mentions) features.

The name HOTCoref stands for Higher Order Tree Coreference. Higher order features is a term often used to describe non-local features in the context of dependency parsing.

The system obtains the best results published to date on all languages from the CoNLL 2012 Shared Task. It is written entirely in Java and is thus platform independent. The download package below includes binaries and sources and a description how to replicate the experiments from the paper.

The system is licensed under the GNU General Public License (GPL). For questions contact Anders Björkelund (firstname@ims.uni-stuttgart.de)

Reference
  • Anders Björkelund and Jonas Kuhn. Learning Structured Perceptrons for Coreference Resolution with Latent Antecedents and Non-local Features. Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). [pdf] [slides] [bibtex]
Download

The system can be downloaded here.

Here's also two pre-trained models for English. They were both trained on the concatenation of the English training and development data.

Jonas Kuhn
Prof. Dr.

Jonas Kuhn

Chair of Foundations of Computational Linguistics, Managing Director of the IMS

To the top of the page