Talla at SemEval-2018 Task 7: Hybrid Loss Optimization for Relation Classification using Convolutional Neural Networks

Bhanu Pratap, Daniel Shank, Oladipo Ositelu, Byron Galbraith


Abstract
This paper describes our approach to SemEval-2018 Task 7 – given an entity-tagged text from the ACL Anthology corpus, identify and classify pairs of entities that have one of six possible semantic relationships. Our model consists of a convolutional neural network leveraging pre-trained word embeddings, unlabeled ACL-abstracts, and multiple window sizes to automatically learn useful features from entity-tagged sentences. We also experiment with a hybrid loss function, a combination of cross-entropy loss and ranking loss, to boost the separation in classification scores. Lastly, we include WordNet-based features to further improve the performance of our model. Our best model achieves an F1(macro) score of 74.2 and 84.8 on subtasks 1.1 and 1.2, respectively.
Anthology ID:
S18-1139
Volume:
Proceedings of the 12th International Workshop on Semantic Evaluation
Month:
June
Year:
2018
Address:
New Orleans, Louisiana
Editors:
Marianna Apidianaki, Saif M. Mohammad, Jonathan May, Ekaterina Shutova, Steven Bethard, Marine Carpuat
Venue:
SemEval
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
863–867
Language:
URL:
https://aclanthology.org/S18-1139
DOI:
10.18653/v1/S18-1139
Bibkey:
Cite (ACL):
Bhanu Pratap, Daniel Shank, Oladipo Ositelu, and Byron Galbraith. 2018. Talla at SemEval-2018 Task 7: Hybrid Loss Optimization for Relation Classification using Convolutional Neural Networks. In Proceedings of the 12th International Workshop on Semantic Evaluation, pages 863–867, New Orleans, Louisiana. Association for Computational Linguistics.
Cite (Informal):
Talla at SemEval-2018 Task 7: Hybrid Loss Optimization for Relation Classification using Convolutional Neural Networks (Pratap et al., SemEval 2018)
Copy Citation:
PDF:
https://aclanthology.org/S18-1139.pdf