期刊
ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2019: TEXT AND TIME SERIES, PT IV
卷 11730, 期 -, 页码 93-103出版社
SPRINGER INTERNATIONAL PUBLISHING AG
DOI: 10.1007/978-3-030-30490-4_9
关键词
Target-dependent sentiment classification; Sentiment classification; Sentiment analysis; Attention mechanism
资金
- National Natural Science Foundation of China [61673403, U1611262]
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-ofthe-art results. Experiments and analysis demonstrate the effectiveness and lightweight of our model.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据