CX-ST-RNM at SemEval-2019 Task 3: Fusion of Recurrent Neural Networks Based on Contextualized and Static Word Representations for Contextual Emotion Detection

Michał Perełkiewicz


Abstract
In this paper, I describe a fusion model combining contextualized and static word representations for approaching the EmoContext task in the SemEval 2019 competition. The model is based on two Recurrent Neural Networks, the first one is fed with a state-of-the-art ELMo deep contextualized word representation and the second one is fed with a static Word2Vec embedding augmented with 10-dimensional affective word feature vector. The proposed model is compared with two baseline models based on a static word representation and a contextualized word representation, separately. My approach achieved officially 0.7278 microaveraged F1 score on the test dataset, ranking 47th out of 165 participants.
Anthology ID:
S19-2028
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:
180–184
Language:
URL:
https://aclanthology.org/S19-2028
DOI:
10.18653/v1/S19-2028
Bibkey:
Cite (ACL):
Michał Perełkiewicz. 2019. CX-ST-RNM at SemEval-2019 Task 3: Fusion of Recurrent Neural Networks Based on Contextualized and Static Word Representations for Contextual Emotion Detection. In Proceedings of the 13th International Workshop on Semantic Evaluation, pages 180–184, Minneapolis, Minnesota, USA. Association for Computational Linguistics.
Cite (Informal):
CX-ST-RNM at SemEval-2019 Task 3: Fusion of Recurrent Neural Networks Based on Contextualized and Static Word Representations for Contextual Emotion Detection (Perełkiewicz, SemEval 2019)
Copy Citation:
PDF:
https://aclanthology.org/S19-2028.pdf
Data
EmoContext