The CLaC Discourse Parser at CoNLL-2016
Computation and Language
2017-08-22 v1
Abstract
This paper describes our submission "CLaC" to the CoNLL-2016 shared task on shallow discourse parsing. We used two complementary approaches for the task. A standard machine learning approach for the parsing of explicit relations, and a deep learning approach for non-explicit relations. Overall, our parser achieves an F1-score of 0.2106 on the identification of discourse relations (0.3110 for explicit relations and 0.1219 for non-explicit relations) on the blind CoNLL-2016 test set.
Cite
@article{arxiv.1708.05798,
title = {The CLaC Discourse Parser at CoNLL-2016},
author = {Majid Laali and Andre Cianflone and Leila Kosseim},
journal= {arXiv preprint arXiv:1708.05798},
year = {2017}
}
Comments
In Proceedings of the Twentieth Conference on Computational Natural Language Learning: Shared Task. pp 92-99. July 7-12, 2016. Berlin, Germany