Interpretable Emoji Prediction via Label-Wise Attention LSTMs

Francesco Barbieri, Luis Espinosa-Anke, Jose Camacho-Collados, Steven Schockaert, Horacio Saggion


Abstract
Human language has evolved towards newer forms of communication such as social media, where emojis (i.e., ideograms bearing a visual meaning) play a key role. While there is an increasing body of work aimed at the computational modeling of emoji semantics, there is currently little understanding about what makes a computational model represent or predict a given emoji in a certain way. In this paper we propose a label-wise attention mechanism with which we attempt to better understand the nuances underlying emoji prediction. In addition to advantages in terms of interpretability, we show that our proposed architecture improves over standard baselines in emoji prediction, and does particularly well when predicting infrequent emojis.
Anthology ID:
D18-1508
Volume:
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Month:
October-November
Year:
2018
Address:
Brussels, Belgium
Editors:
Ellen Riloff, David Chiang, Julia Hockenmaier, Jun’ichi Tsujii
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
4766–4771
Language:
URL:
https://aclanthology.org/D18-1508
DOI:
10.18653/v1/D18-1508
Bibkey:
Cite (ACL):
Francesco Barbieri, Luis Espinosa-Anke, Jose Camacho-Collados, Steven Schockaert, and Horacio Saggion. 2018. Interpretable Emoji Prediction via Label-Wise Attention LSTMs. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 4766–4771, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Interpretable Emoji Prediction via Label-Wise Attention LSTMs (Barbieri et al., EMNLP 2018)
Copy Citation:
PDF:
https://aclanthology.org/D18-1508.pdf
Video:
 https://aclanthology.org/D18-1508.mp4