Multi-task Learning of Negation and Speculation for Targeted Sentiment Classification

Andrew Moore, Jeremy Barnes


Abstract
The majority of work in targeted sentiment analysis has concentrated on finding better methods to improve the overall results. Within this paper we show that these models are not robust to linguistic phenomena, specifically negation and speculation. In this paper, we propose a multi-task learning method to incorporate information from syntactic and semantic auxiliary tasks, including negation and speculation scope detection, to create English-language models that are more robust to these phenomena. Further we create two challenge datasets to evaluate model performance on negated and speculative samples. We find that multi-task models and transfer learning via language modelling can improve performance on these challenge datasets, but the overall performances indicate that there is still much room for improvement. We release both the datasets and the source code at https://github.com/jerbarnes/multitask_negation_for_targeted_sentiment.
Anthology ID:
2021.naacl-main.227
Volume:
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
June
Year:
2021
Address:
Online
Editors:
Kristina Toutanova, Anna Rumshisky, Luke Zettlemoyer, Dilek Hakkani-Tur, Iz Beltagy, Steven Bethard, Ryan Cotterell, Tanmoy Chakraborty, Yichao Zhou
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2838–2869
Language:
URL:
https://aclanthology.org/2021.naacl-main.227
DOI:
10.18653/v1/2021.naacl-main.227
Bibkey:
Cite (ACL):
Andrew Moore and Jeremy Barnes. 2021. Multi-task Learning of Negation and Speculation for Targeted Sentiment Classification. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2838–2869, Online. Association for Computational Linguistics.
Cite (Informal):
Multi-task Learning of Negation and Speculation for Targeted Sentiment Classification (Moore & Barnes, NAACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.naacl-main.227.pdf
Optional supplementary data:
 2021.naacl-main.227.OptionalSupplementaryData.zip
Optional supplementary code:
 2021.naacl-main.227.OptionalSupplementaryCode.zip
Video:
 https://aclanthology.org/2021.naacl-main.227.mp4
Code
 jerbarnes/multitask_negation_for_targeted_sentiment +  additional community code
Data
MAMSMPQA Opinion Corpus