Home > Research > Publications & Outputs > Multi-layer Attention Based CNN for Target-Depe...

Research

Links

Text available via DOI:

View graph of relations

Multi-layer Attention Based CNN for Target-Dependent Sentiment Classification

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

Multi-layer Attention Based CNN for Target-Dependent Sentiment Classification. / Zhang, S.; Xu, X.; Pang, Y. et al.
In: Neural Processing Letters, Vol. 51, No. 3, 01.06.2020, p. 2089-2103.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Zhang, S, Xu, X, Pang, Y & Han, J 2020, 'Multi-layer Attention Based CNN for Target-Dependent Sentiment Classification', Neural Processing Letters, vol. 51, no. 3, pp. 2089-2103. https://doi.org/10.1007/s11063-019-10017-9

APA

Zhang, S., Xu, X., Pang, Y., & Han, J. (2020). Multi-layer Attention Based CNN for Target-Dependent Sentiment Classification. Neural Processing Letters, 51(3), 2089-2103. https://doi.org/10.1007/s11063-019-10017-9

Vancouver

Zhang S, Xu X, Pang Y, Han J. Multi-layer Attention Based CNN for Target-Dependent Sentiment Classification. Neural Processing Letters. 2020 Jun 1;51(3):2089-2103. Epub 2019 Mar 9. doi: 10.1007/s11063-019-10017-9

Author

Zhang, S. ; Xu, X. ; Pang, Y. et al. / Multi-layer Attention Based CNN for Target-Dependent Sentiment Classification. In: Neural Processing Letters. 2020 ; Vol. 51, No. 3. pp. 2089-2103.

Bibtex

@article{baca87a6421a411593a57147d7acf5bf,
title = "Multi-layer Attention Based CNN for Target-Dependent Sentiment Classification",
abstract = "Target-dependent sentiment classification aims at identifying the sentiment polarities of targets in a given sentence. Previous approaches utilize recurrent neural network with attention mechanism incorporated to model the context and learn key sentiment intermediate representation in relation to a given target. However, such methods are incapable either of modeling complex contexts or of processing data parallelly. To address these problems, we propose, in this paper, a new model that employs a multi-layer convolutional neural network to process the context parallelly and model the context multiple times, where the neural network is able to explicitly learn the sentiment intermediate representation via an attention mechanism. Eventually, we integrate these features to form a final sentiment representation, which will be fed into the classifier. Experiments show that our model surpasses the existing approaches on several datasets.",
author = "S. Zhang and X. Xu and Y. Pang and J. Han",
year = "2020",
month = jun,
day = "1",
doi = "10.1007/s11063-019-10017-9",
language = "English",
volume = "51",
pages = "2089--2103",
journal = "Neural Processing Letters",
issn = "1370-4621",
publisher = "Springer",
number = "3",

}

RIS

TY - JOUR

T1 - Multi-layer Attention Based CNN for Target-Dependent Sentiment Classification

AU - Zhang, S.

AU - Xu, X.

AU - Pang, Y.

AU - Han, J.

PY - 2020/6/1

Y1 - 2020/6/1

N2 - Target-dependent sentiment classification aims at identifying the sentiment polarities of targets in a given sentence. Previous approaches utilize recurrent neural network with attention mechanism incorporated to model the context and learn key sentiment intermediate representation in relation to a given target. However, such methods are incapable either of modeling complex contexts or of processing data parallelly. To address these problems, we propose, in this paper, a new model that employs a multi-layer convolutional neural network to process the context parallelly and model the context multiple times, where the neural network is able to explicitly learn the sentiment intermediate representation via an attention mechanism. Eventually, we integrate these features to form a final sentiment representation, which will be fed into the classifier. Experiments show that our model surpasses the existing approaches on several datasets.

AB - Target-dependent sentiment classification aims at identifying the sentiment polarities of targets in a given sentence. Previous approaches utilize recurrent neural network with attention mechanism incorporated to model the context and learn key sentiment intermediate representation in relation to a given target. However, such methods are incapable either of modeling complex contexts or of processing data parallelly. To address these problems, we propose, in this paper, a new model that employs a multi-layer convolutional neural network to process the context parallelly and model the context multiple times, where the neural network is able to explicitly learn the sentiment intermediate representation via an attention mechanism. Eventually, we integrate these features to form a final sentiment representation, which will be fed into the classifier. Experiments show that our model surpasses the existing approaches on several datasets.

U2 - 10.1007/s11063-019-10017-9

DO - 10.1007/s11063-019-10017-9

M3 - Journal article

VL - 51

SP - 2089

EP - 2103

JO - Neural Processing Letters

JF - Neural Processing Letters

SN - 1370-4621

IS - 3

ER -