Interactive Multi-Head Attention Networks for Aspect-Level Sentiment Classification

Aspect-Based (also known as aspect-level) Sentiment Classification (ABSC) aims at determining the sentimental tendency of a particular target in a sentence. With the successful application of the attention network in multiple fields, attention-based ABSC has aroused great interest. However, most of the previous methods are difficult to parallelize, insufficiently obtain, and fuse the interactive information. In this paper, we proposed a Multiple Interactive Attention Network (MIN). First, we used the Bidirectional Encoder Representations from Transformers (BERT) model to pre-process the data. Then, we used the partial transformer to obtain a hidden state in parallel. Finally, we took the target word and the context word as the core to obtain and fuse the interactive information. Experimental results on the different datasets showed that our model was much more effective.

Download Full-text

Surrounding-Based Attention Networks for Aspect-Level Sentiment Classification

Artificial Neural Networks and Machine Learning – ICANN 2019: Text and Time Series - Lecture Notes in Computer Science ◽

10.1007/978-3-030-30490-4_13 ◽

2019 ◽

pp. 143-155

Author(s):

Yuheng Sun ◽

Xianchen Wang ◽

Hongtao Liu ◽

Wenjun Wang ◽

Pengfei Jiao

Keyword(s):

Sentiment Classification ◽

Attention Networks

Download Full-text

Aspect Sentiment Classification with both Word-level and Clause-level Attention Networks

Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2018/617 ◽

2018 ◽

Cited By ~ 10

Author(s):

Jingjing Wang ◽

Jie Li ◽

Shoushan Li ◽

Yangyang Kang ◽

Min Zhang ◽

...

Keyword(s):

Sentiment Analysis ◽

Sentiment Classification ◽

Experimental Results ◽

Hierarchical Network ◽

Attention Networks ◽

Word Level ◽

Sentence Level

Aspect sentiment classification, a challenging task in sentiment analysis, has been attracting more and more attention in recent years. In this paper, we highlight the need for incorporating the importance degrees of both words and clauses inside a sentence and propose a hierarchical network with both word-level and clause-level attentions to aspect sentiment classification. Specifically, we first adopt sentence-level discourse segmentation to segment a sentence into several clauses. Then, we leverage multiple Bi-directional LSTM layers to encode all clauses and propose a word-level attention layer to capture the importance degrees of words in each clause. Third and finally, we leverage another Bi-directional LSTM layer to encode the outputs from the former layers and propose a clause-level attention layer to capture the importance degrees of all the clauses inside a sentence. Experimental results on the laptop and restaurant datasets from SemEval-2015 demonstrate the effectiveness of our proposed approach to aspect sentiment classification.

Download Full-text