Internet Archive Scholar

IIIDYT at IEST 2018: Implicit Emotion Classification With Deep Contextualized Word Representations

Jorge Balazs, Edison Marrese-Taylor, Yutaka Matsuo
2018 Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (1.1 MB)
https://web.archive.org/web/20200507201209/https://www.aclweb.org/anthology/W18-6208.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL. The file type is application/pdf.

In this paper we describe our system designed for the WASSA 2018 Implicit Emotion Shared Task (IEST), which obtained 2 nd place out of 30 teams with a test macro F1 score of 0.710. The system is composed of a single pre-trained ELMo layer for encoding words, a Bidirectional Long-Short Memory Network BiLSTM for enriching word representations with context, a max-pooling operation for creating sentence representations from them, and a Dense Layer for projecting the sentence representations into
more » ... el space. Our official submission was obtained by ensembling 6 of these models initialized with different random seeds. The code for replicating this paper is available at https://github.com/ jabalazs/implicit_emotion.
doi:10.18653/v1/w18-6208 dblp:conf/wassa/BalazsMM18 fatcat:zdccok5nbjhcxkgkhbkmlm4v2m
Citation

Jorge Balazs, Edison Marrese-Taylor, Yutaka Matsuo. "IIIDYT at IEST 2018: Implicit Emotion Classification With Deep Contextualized Word Representations." Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis (2018) 50-56