Attentional Encoder Network for Targeted Sentiment Classification

Youwei Song, Jiahai Wang, Tao Jiang, Zhiyue Liu, Yanghui Rao
2/25/2019
cs.CL

Official code: songyouwei/ABSA-PyTorch (2,114 stars, MIT, last commit 2023-06-12).

Abstract

Targeted sentiment classification aims at determining the sentimental tendency towards specific targets. Most of the previous approaches model context and target words with RNN and attention. However, RNNs are difficult to parallelize and truncated backpropagation through time brings difficulty in remembering long-term patterns. To address this issue, this paper proposes an Attentional Encoder Network (AEN) which eschews recurrence and employs attention based encoders for the modeling between context and target. We raise the label unreliability issue and introduce label smoothing regularization. We also apply pre-trained BERT to this task and obtain new state-of-the-art results. Experiments and analysis demonstrate the effectiveness and lightweight of our model.

View on arXivView PDF

Code Implementations(1)

songyouwei/ABSA-PyTorchOfficial100%
MIT

Aspect Based Sentiment Analysis, PyTorch Implementations. 基于方面的情感分析，使用PyTorch实现。

2,114519PythonMay 9, 20183 years agoMIT
aspect-based-sentiment-analysisattentionbertnatural-language-processingnlp+2 more

Similar Papers

Transformation Networks for Target-Oriented Sentiment Classification

87% match1 repo1392018

Studying Attention Models in Sentiment Attitude Extraction Task

84% match2020

IndoBERT-Sentiment: Context-Conditioned Sentiment Classification for Indonesian Text

84% match2026

Joint Learning of Local and Global Features for Aspect-based Sentiment Classification

84% match2023

Generative Sentiment Transfer via Adaptive Masking

82% match2023

Aspect-Based Sentiment Analysis using Local Context Focus Mechanism with DeBERTa

81% match2022

Cite this paper

@article{song2019attentional,
  title  = {Attentional Encoder Network for Targeted Sentiment Classification},
  author = {Youwei Song and Jiahai Wang and Tao Jiang and Zhiyue Liu and Yanghui Rao},
  year   = {2019},
  eprint = {1902.09314},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1902.09314}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1902.09314.svg)](https://codeofpaper.com/paper/1902.09314)

Discussion