# Context-aware Embedding for Targeted Aspect-based Sentiment Analysis

## TL;DR

This paper introduces a novel embedding refinement method for targeted aspect-based sentiment analysis that enhances context-dependent representations of targets and aspects, leading to improved performance.

## Contribution

It proposes a sparse coefficient-based embedding refinement technique specifically designed for TABSA, addressing the limitations of context-independent embeddings.

## Key findings

- Achieved state-of-the-art results on two benchmark datasets.
- Demonstrated significant performance improvements over existing methods.
- Validated the effectiveness of context-aware embedding refinement.

## Abstract

Attention-based neural models were employed to detect the different aspects and sentiment polarities of the same target in targeted aspect-based sentiment analysis (TABSA). However, existing methods do not specifically pre-train reasonable embeddings for targets and aspects in TABSA. This may result in targets or aspects having the same vector representations in different contexts and losing the context-dependent information. To address this problem, we propose a novel method to refine the embeddings of targets and aspects. Such pivotal embedding refinement utilizes a sparse coefficient vector to adjust the embeddings of target and aspect from the context. Hence the embeddings of targets and aspects can be refined from the highly correlative words instead of using context-independent or randomly initialized vectors. Experiment results on two benchmark datasets show that our approach yields the state-of-the-art performance in TABSA task.