Beck, D., Cohn, T. and Specia, L. orcid.org/0000-0002-5495-3128 (2014) Joint Emotion Analysis via Multi-task Gaussian Processes. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). EMNLP, October 25-29, 2014, Doha, Qatar. ACL , pp. 1798-1803.
Abstract
We propose a model for jointly predicting multiple emotions in natural language sentences. Our model is based on a low-rank coregionalisation approach, which combines a vector-valued Gaussian Process with a rich parameterisation scheme. We show that our approach is able to learn correlations and anti-correlations between emotions on a news headlines dataset. The proposed model outperforms both singletask baselines and other multi-task approaches.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2014 Association for Computational Linguistics. Article licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 License . Permission is granted to make copies for the purposes of teaching and research |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield) |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 16 Aug 2016 13:30 |
Last Modified: | 16 Aug 2016 13:30 |
Published Version: | http://www.aclweb.org/anthology/D14-1190 |
Status: | Published |
Publisher: | ACL |
Refereed: | Yes |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:98288 |