Attentional Encoder Network for Targeted Sentiment Classification
Youwei Song, Jiahai Wang, Tao Jiang, Zhiyue Liu, Yanghui Rao
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/songyouwei/ABSA-PyTorchOfficialIn paperpytorch★ 0
- github.com/yangheng95/LC-ABSApytorch★ 1,088
- github.com/recommeddit/labspytorch★ 1
- github.com/Ankur3107/awesome-daily-blogtf★ 0
- github.com/mindspore-courses/ABSA-MindSporemindspore★ 0
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.
Tasks
Benchmark Results
| Dataset | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| SemEval-2014 Task-4 | BERT-SPC | Mean Acc (Restaurant + Laptop) | 81.73 | — | Unverified |
| SemEval-2014 Task-4 | AEN-BERT | Mean Acc (Restaurant + Laptop) | 81.53 | — | Unverified |
| SemEval-2014 Task-4 | AEN-GloVe | Mean Acc (Restaurant + Laptop) | 77.25 | — | Unverified |