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

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

16 Oct 2020NAACL 2021 4arXiv:2010.08318archive 2025-07-28

Andrew Moore, Jeremy Barnes

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.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

jerbarnes/multitask_negation_for_targeted_sentiment officialmentioned in papermentioned on GitHubpytorch report
apmoore1/language-model officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

General ClassificationLanguage ModellingMulti-Task LearningNegationSentiment AnalysisSentiment ClassificationTransfer Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections