Work

Lexicon information in neural sentiment analysis: a multi-task learning approach.

Year: 2019

Type: article

Abstract: This paper explores the use of multi-task learning (MTL) for incorporating external knowledge in neural models.Specifically, we show how MTL can enable a BiLSTM sentiment classifier to incorporate information from sentiment lexicons.Our MTL set-up is shown to improve model performance (compared to a single-task set-up) on both English and Norwegian sentence-level sentiment datasets.The paper also introduces a new sentiment lexicon for Norwegian.

Source: DSpace repository (University of Tartu)

Authors: Jeremy Claude Barnes, Samia Touileb, Lilja Øvrelid, Erik Velldal

Language: English

Topic: Sentiment Analysis and Opinion Mining

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: Norges Forskningsråd

Award: SANT: Sentiment Analysis for Norwegian Text

OpenAlex ID: W2982578217

FWCI: 0.902

Cites: 46

Cited by: 10

Related to: 10