Paper: BART goes multilingual: The UniTN / Essex submission to the CoNLL-2012 Shared Task

ACL ID W12-4515
Title BART goes multilingual: The UniTN / Essex submission to the CoNLL-2012 Shared Task
Venue International Conference on Computational Natural Language Learning
Session shared task
Year 2012
Authors

This paper describes the UniTN/Essex sub- mission to the CoNLL-2012 Shared Task on the Multilingual Coreference Resolution. We have extended our CoNLL-2011 submission, based on BART, to cover two additional lan- guages, Arabic and Chinese. This paper fo- cuses on adapting BART to new languages, discussing the problems we have encountered and the solutions adopted. In particular, we propose a novel entity-mention detection algo- rithm that might help identify nominal men- tions in an unknown language. We also dis- cuss the impact of basic linguistic information on the overall performance level of our coref- erence resolution system.