Abstract | ||
---|---|---|
Memory networks have shown expressive performance on aspect based sentiment analysis. However, ordinary memory networks only capture word-level information and lack the capacity for modeling complicated expressions which consist of multiple words. Targeting this problem, we propose a novel convolutional memory network which incorporates an attention mechanism. This model sequentially computes the weights of multiple memory units corresponding to multi-words. This model may capture both words and multi-words expressions in sentences for aspect-based sentiment analysis. Experimental results show that the proposed model outperforms the state-of-the-art baselines.
|
Year | DOI | Venue |
---|---|---|
2018 | 10.1145/3209978.3210115 | SIGIR |
Keywords | Field | DocType |
sentiment analysis,memory network,convolutional operation | Data mining,Expression (mathematics),Convolution,Sentiment analysis,Computer science | Conference |
ISBN | Citations | PageRank |
978-1-4503-5657-2 | 2 | 0.37 |
References | Authors | |
8 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chuang Fan | 1 | 4 | 1.45 |
Qinghong Gao | 2 | 4 | 0.73 |
Du Jiachen | 3 | 36 | 9.02 |
Lin Gui | 4 | 18 | 6.43 |
Xu Ruifeng | 5 | 432 | 53.04 |
Kam-Fai Wong | 6 | 1718 | 176.33 |