USI-IR at IEST 2018: Sequence Modeling and Pseudo-Relevance Feedback for Implicit Emotion Detection

Esteban Ríssola, Anastasia Giachanou, Fabio Crestani


Abstract
This paper describes the participation of USI-IR in WASSA 2018 Implicit Emotion Shared Task. We propose a relevance feedback approach employing a sequential model (biLSTM) and word embeddings derived from a large collection of tweets. To this end, we assume that the top-k predictions produce at a first classification step are correct (based on the model accuracy) and use them as new examples to re-train the network.
Anthology ID:
W18-6233
Volume:
Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis
Month:
October
Year:
2018
Address:
Brussels, Belgium
Editors:
Alexandra Balahur, Saif M. Mohammad, Veronique Hoste, Roman Klinger
Venue:
WASSA
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
231–234
Language:
URL:
https://aclanthology.org/W18-6233
DOI:
10.18653/v1/W18-6233
Bibkey:
Cite (ACL):
Esteban Ríssola, Anastasia Giachanou, and Fabio Crestani. 2018. USI-IR at IEST 2018: Sequence Modeling and Pseudo-Relevance Feedback for Implicit Emotion Detection. In Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, pages 231–234, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
USI-IR at IEST 2018: Sequence Modeling and Pseudo-Relevance Feedback for Implicit Emotion Detection (Ríssola et al., WASSA 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/improve-issue-templates/W18-6233.pdf