Abstract
This paper reports the submitted discourse relation classification systems of the language information processing group of Beijing Institute of Technology (BIT) to the CoNLL-2016 shared task. In this work, discriminative methods were employed according to the different characteristics of English and Chinese discourse structures. Additionally, distributed representations were introduced to catch the deep semantic relations. Experiments shows their effectiveness on both English and Chinese tasks.
Cite
CITATION STYLE
Jian, P., She, X., Zhang, C., Zhang, P., & Feng, J. (2016). Discourse relation sense classification systems for CoNLL-2016 shared task. In Proceedings of the 20th SIGNLL Conference on Computational Natural Language Learning: Shared Task, CoNLL 2016 (pp. 158–163). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/k16-2022
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
