UNH at SemEval-2019 Task 12: Toponym Resolution in Scientific Papers

Matthew Magnusson, Laura Dietz


Abstract
The SemEval-2019 Task 12 is toponym resolution in scientific papers. We focus on Subtask 1: Toponym Detection which is the identification of spans of text for place names mentioned in a document. We propose two methods: 1) sliding window convolutional neural network using ELMo embeddings (cnn-elmo), and 2) sliding window multi-Layer perceptron using ELMo embeddings (mlp-elmo). We also submit Bi-lateral LSTM with Conditional Random Fields (bi-LSTM) as a strong baseline given its state-of-art performance in Named Entity Recognition (NER) task. Our best performing model is cnn-elmo with a F1 of 0.844 which was below bi-LSTM F1 of 0.862 when evaluated on overlap macro detection. Eight teams participated in this subtask with a total of 21 submissions.
Anthology ID:
S19-2230
Volume:
Proceedings of the 13th International Workshop on Semantic Evaluation
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota, USA
Editors:
Jonathan May, Ekaterina Shutova, Aurelie Herbelot, Xiaodan Zhu, Marianna Apidianaki, Saif M. Mohammad
Venue:
SemEval
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
1308–1312
Language:
URL:
https://aclanthology.org/S19-2230
DOI:
10.18653/v1/S19-2230
Bibkey:
Cite (ACL):
Matthew Magnusson and Laura Dietz. 2019. UNH at SemEval-2019 Task 12: Toponym Resolution in Scientific Papers. In Proceedings of the 13th International Workshop on Semantic Evaluation, pages 1308–1312, Minneapolis, Minnesota, USA. Association for Computational Linguistics.
Cite (Informal):
UNH at SemEval-2019 Task 12: Toponym Resolution in Scientific Papers (Magnusson & Dietz, SemEval 2019)
Copy Citation:
PDF:
https://aclanthology.org/S19-2230.pdf