From Sentiment Annotations to Sentiment Prediction through Discourse Augmentation

Patrick Huber, Giuseppe Carenini


Abstract
Sentiment analysis, especially for long documents, plausibly requires methods capturing complex linguistics structures. To accommodate this, we propose a novel framework to exploit task-related discourse for the task of sentiment analysis. More specifically, we are combining the large-scale, sentiment-dependent MEGA-DT treebank with a novel neural architecture for sentiment prediction, based on a hybrid TreeLSTM hierarchical attention model. Experiments show that our framework using sentiment-related discourse augmentations for sentiment prediction enhances the overall performance for long documents, even beyond previous approaches using well-established discourse parsers trained on human annotated data. We show that a simple ensemble approach can further enhance performance by selectively using discourse, depending on the document length.
Anthology ID:
2020.coling-main.16
Volume:
Proceedings of the 28th International Conference on Computational Linguistics
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Editors:
Donia Scott, Nuria Bel, Chengqing Zong
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
185–197
Language:
URL:
https://aclanthology.org/2020.coling-main.16
DOI:
10.18653/v1/2020.coling-main.16
Bibkey:
Cite (ACL):
Patrick Huber and Giuseppe Carenini. 2020. From Sentiment Annotations to Sentiment Prediction through Discourse Augmentation. In Proceedings of the 28th International Conference on Computational Linguistics, pages 185–197, Barcelona, Spain (Online). International Committee on Computational Linguistics.
Cite (Informal):
From Sentiment Annotations to Sentiment Prediction through Discourse Augmentation (Huber & Carenini, COLING 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.coling-main.16.pdf