Scubed at 3C task B - A simple baseline for citation context influence classification

Shubhanshu Mishra, Sudhanshu Mishra


Abstract
We present our team Scubed’s approach in the 3C Citation Context Classification Task, Subtask B, citation context influence classification. Our approach relies on text based features transformed via tf-idf features followed by training a variety of simple models resulting in a strong baseline. Our best model on the leaderboard is a random forest classifier using only the citation context text. A replication of our analysis finds logistic regression and gradient boosted tree classifier to be the best performing model. Our submission code can be found at: https://github.com/napsternxg/Citation_Context_Classification.
Anthology ID:
2020.wosp-1.10
Volume:
Proceedings of the 8th International Workshop on Mining Scientific Publications
Month:
05 August
Year:
2020
Address:
Wuhan, China
Venue:
WOSP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
65–70
Language:
URL:
https://aclanthology.org/2020.wosp-1.10
DOI:
Bibkey:
Cite (ACL):
Shubhanshu Mishra and Sudhanshu Mishra. 2020. Scubed at 3C task B - A simple baseline for citation context influence classification. In Proceedings of the 8th International Workshop on Mining Scientific Publications, pages 65–70, Wuhan, China. Association for Computational Linguistics.
Cite (Informal):
Scubed at 3C task B - A simple baseline for citation context influence classification (Mishra & Mishra, WOSP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.wosp-1.10.pdf
Code
 napsternxg/citation_context_classification