TY - GEN
T1 - Targeted sentiment classification with knowledge powered attention network
AU - Bian, Ximo
AU - Feng, Chong
AU - Ahmad, Arshad
AU - Dai, Jinming
AU - Zhao, Guifen
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/11
Y1 - 2019/11
N2 - Targeted sentiment classification aims to identify the sentiment expressed towards some targets given context sentences, having great application value in social media, ecommerce platform and other fields. Most of the previous methods model context and target words with RNN and attention mechanism, which primarily do not use any external knowledge. In this paper, we utilize external knowledge from knowledge bases to reinforce the semantic representation of context and target. We propose a new model called Knowledge Powered Attention Network (KPAN), which uses the multi-head attention mechanism to represent target and context and to fuse with conceptual knowledge extracted from external knowledge bases. The experiments on three public datasets revealed that our proposed model outperforms the state-of-the-art methods, which signify the validity of our model.
AB - Targeted sentiment classification aims to identify the sentiment expressed towards some targets given context sentences, having great application value in social media, ecommerce platform and other fields. Most of the previous methods model context and target words with RNN and attention mechanism, which primarily do not use any external knowledge. In this paper, we utilize external knowledge from knowledge bases to reinforce the semantic representation of context and target. We propose a new model called Knowledge Powered Attention Network (KPAN), which uses the multi-head attention mechanism to represent target and context and to fuse with conceptual knowledge extracted from external knowledge bases. The experiments on three public datasets revealed that our proposed model outperforms the state-of-the-art methods, which signify the validity of our model.
KW - Attention network
KW - External knowledge
KW - Targeted sentiment classification
UR - http://www.scopus.com/inward/record.url?scp=85081092876&partnerID=8YFLogxK
U2 - 10.1109/ICTAI.2019.00150
DO - 10.1109/ICTAI.2019.00150
M3 - Conference contribution
AN - SCOPUS:85081092876
T3 - Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI
SP - 1073
EP - 1080
BT - Proceedings - IEEE 31st International Conference on Tools with Artificial Intelligence, ICTAI 2019
PB - IEEE Computer Society
T2 - 31st IEEE International Conference on Tools with Artificial Intelligence, ICTAI 2019
Y2 - 4 November 2019 through 6 November 2019
ER -