CLaC-np at SemEval-2021 Task 8: Dependency DGCNN

Nihatha Lathiff, Pavel PK Khloponin, Sabine Bergler


Abstract
MeasEval aims at identifying quantities along with the entities that are measured with additional properties within English scientific documents. The variety of styles used makes measurements, a most crucial aspect of scientific writing, challenging to extract. This paper presents ablation studies making the case for several preprocessing steps such as specialized tokenization rules. For linguistic structure, we encode dependency trees in a Deep Graph Convolution Network (DGCNN) for multi-task classification.
Anthology ID:
2021.semeval-1.48
Volume:
Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)
Month:
August
Year:
2021
Address:
Online
Editors:
Alexis Palmer, Nathan Schneider, Natalie Schluter, Guy Emerson, Aurelie Herbelot, Xiaodan Zhu
Venue:
SemEval
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
404–409
Language:
URL:
https://aclanthology.org/2021.semeval-1.48
DOI:
10.18653/v1/2021.semeval-1.48
Bibkey:
Cite (ACL):
Nihatha Lathiff, Pavel PK Khloponin, and Sabine Bergler. 2021. CLaC-np at SemEval-2021 Task 8: Dependency DGCNN. In Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021), pages 404–409, Online. Association for Computational Linguistics.
Cite (Informal):
CLaC-np at SemEval-2021 Task 8: Dependency DGCNN (Lathiff et al., SemEval 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.semeval-1.48.pdf