Home > Research > Publications & Outputs > Multi-task Learning of Negation and Speculation...

Electronic data

View graph of relations

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

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published

Standard

Multi-task Learning of Negation and Speculation for Targeted Sentiment Classification. / Moore, Andrew; Barnes, Jeremy.
The 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg, Pa: Association for Computational Linguistics, 2021. p. 2838-2869 227.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Harvard

Moore, A & Barnes, J 2021, Multi-task Learning of Negation and Speculation for Targeted Sentiment Classification. in The 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies., 227, Association for Computational Linguistics, Stroudsburg, Pa, pp. 2838-2869.

APA

Moore, A., & Barnes, J. (2021). Multi-task Learning of Negation and Speculation for Targeted Sentiment Classification. In The 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (pp. 2838-2869). Article 227 Association for Computational Linguistics.

Vancouver

Moore A, Barnes J. Multi-task Learning of Negation and Speculation for Targeted Sentiment Classification. In The 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg, Pa: Association for Computational Linguistics. 2021. p. 2838-2869. 227

Author

Moore, Andrew ; Barnes, Jeremy. / Multi-task Learning of Negation and Speculation for Targeted Sentiment Classification. The 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg, Pa : Association for Computational Linguistics, 2021. pp. 2838-2869

Bibtex

@inproceedings{6473dbec0eb54df3bc096398495c508e,
title = "Multi-task Learning of Negation and Speculation for Targeted Sentiment Classification",
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.",
keywords = "NLP , Sentiment Analysis",
author = "Andrew Moore and Jeremy Barnes",
year = "2021",
month = may,
day = "23",
language = "English",
pages = "2838--2869",
booktitle = "The 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
publisher = "Association for Computational Linguistics",

}

RIS

TY - GEN

T1 - Multi-task Learning of Negation and Speculation for Targeted Sentiment Classification

AU - Moore, Andrew

AU - Barnes, Jeremy

PY - 2021/5/23

Y1 - 2021/5/23

N2 - 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.

AB - 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.

KW - NLP

KW - Sentiment Analysis

M3 - Conference contribution/Paper

SP - 2838

EP - 2869

BT - The 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

PB - Association for Computational Linguistics

CY - Stroudsburg, Pa

ER -