Aspect-Based Sentiment Analysis using BERT

By Mickel Hoang, Oskar Alija Bihorac, Jacobo Rouces. Nordic Conference of Computational Linguistics, 2019

305 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Beneath the Tip of the Iceberg: Current Challenges and New Directions in Sentiment Analysis Research (2020, methodology): “ang & Carley, 2019). Simple baselines utilizing BERT has demonstrated competitive performances against sophisticated state-of-theart methods (Li et al., 2019b) and also in out-of-domain settings (Hoang et al., 2019). These trends indicate the role of semantic understanding for the task of aspect”
Multimodal Sentiment Analysis: A Survey of Methods, Trends, and Challenges (2023, methodology): “[81] utilized the contextual pre-trained word representations model like BERT combined with a fine-tuning approach with additional generated text for solving out-of-domain aspect-based sentiment analysis problems.”
Improving Document-Level Sentiment Classification Using Importance of Sentences (2020, methodology): “[17] showed that using the contextual word representations from BERT is effective in a sentiment analysis task.”