Aspect-based sentiment analysis (ABSA) is a hot and significant task of natural language processing, which is composed of two subtasks, the aspect term extraction (ATE) and aspect polarity classification (APC). Previous researches generally studied two subtasks independently and designed neural network models for ATE and APC respectively. However, it integrates various manual features into the model, which will consume plenty of computing resources and labor. Moreover, the quality of the ATE results will affect the performance of APC. This paper proposes a multi-task learning model based on dual auxiliary labels for ATE and APC. In this paper, general IOB labels, and sentimental IOB labels are equipped to efficiently solve both ATE and APC tasks without manual features adopted. Experiments are conducted on two general ABSA benchmark datasets of SemEval-2014. The experimental results reveal that the proposed model is of great performance and efficient for both ATE and APC tasks compared to the main baseline models.
HuM. and LiuB., Mining opinion features in customer reviews. In Proceedings of the 19th national conference on Artifical intelligence, (2004), pp. 755–760. AAAI Press.
2.
QiuG., LiuB., BuJ. and ChenC., Opinion word expansion and target extraction through double propagation, Computational Linguistics37(1), 2011.
3.
LaffertyJ., McCallumA. and PereiraF. CN, Conditional random fields: Probabilistic models for segmenting and labeling sequence data. 2001.
4.
HamdanH., BellotP. and BechetF., Lsislif: Crf and logistic regression for opinion target extraction and sentiment polarity analysis. In Proceedings of the 9th international workshop on semantic evaluation (SemEval 2015), (2015), pp. 753–758.
5.
JinW. and HoH.H., A novel lexicalized hmm-based learning framework for web opinion mining. In Proceedings of the 26th Annual International Conference on Machine Learning, (2009), pp. 465–472. ACM.
6.
JakobN. and GurevychI., Extracting opinion targets in a single-and cross-domain setting with conditional random fields. In Proceedings of the 2010 conference on empirical methods in natural language processing, (2010), pp. 1035–1045. Association for Computational Linguistics.
7.
ChernyshevichM., Ihs r&d belarus: Cross-domain extraction of product features using crf. In Proceedings of the 8th international workshop on semantic evaluation (SemEval 2014), (2014), pp. 309–313.
8.
WangW., PanS.J., DahlmeierD. and XiaoX., Recursive neural conditional random fields for aspectbased sentiment analysis. arXiv preprint arXiv:1603.06679, 2016.
9.
XuH., LiuB., ShuL. and PhilipS.Y., Double embeddings and cnn-based sequence labeling for aspect extraction. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), (2018), pp. 592–598.
10.
LuoH., LiT., LiuB., WangB. and UngerH., Improving aspect term extraction with bidirectional dependency tree representation, IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP)27(7) (2019), 1201–1212.
11.
TangD., QinB., FengX. and LiuT., Effective lstms for target-dependent sentiment classification. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, (2016), pp. 3298–3307.
12.
TaiK.S., SocherR. and ManningC.D., Improved semantic representations from tree-structured long short-term memory networks. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)1 (2015), pp. 1556–1566.
13.
WangY., HuangM. and ZhaoL., et al., Attention-based lstm for aspect-level sentiment classification. In Proceedings of the 2016 conference on empirical methods in natural language processing, (2016), pp. 606–615.
14.
MaD., LiS., ZhangX. and WangH., Interactive attention networks for aspect-level sentiment classification. arXiv preprint arXiv:1709.00893, 2017.
15.
XueW. and LiT., Aspect based sentiment analysis with gated convolutional networks. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), (2018), pp. 2514–2523.
16.
XingY., XiaoC., WuY. and DingZ., Aconvolutional neural network for aspect sentiment classification. arXiv preprint arXiv:1807.01704, 2018.
17.
NguyenH. and ShiraiK., A joint model of term extraction and polarity classification for aspect-based sentiment analysis. In 2018 10th International Conference on Knowledge and Systems Engineering (KSE), (2018), pp. 323–328. IEEE.
18.
WangF., LanM. and WangW., Towards a onestop solution to both aspect extraction and sentiment analysis tasks with neural multi-task learning. In 2018 International Joint Conference on Neural Networks (IJCNN), (2018), pp. 1–8. IEEE.
19.
MaD., LiS. and WangH., Joint learning for targeted sentiment analysis. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, (2018), pp. 4737–4742.
20.
HuangZ., XuW. and YuK., Bidirectional lstm-crf models for sequence tagging. arXiv preprint arXiv:1508.01991, 2015.
21.
GravesA., MohamedA.-R. and HintonG., Speech recognition with deep recurrent neural networks. In 2013 IEEE international conference on acoustics, speech and signal processing, (2013), pp. 6645–6649. IEEE.
22.
MikolovT., SutskeverI., ChenK., CorradoG.S. and DeanJ., Distributed representations of words and phrases and their compositionality. In Advances in neural information processing systems, (2013), pp. 3111–3119.
23.
WagnerJ., AroraP., CortesS., BarmanU., BogdanovaD., FosterJ. and TounsiL., Dcu: Aspect-based polarity classification for semeval task 4. In Proceedings of the 8th international workshop on semantic evaluation (SemEval 2014), (2014), pp. 223–229.
24.
TangD., QinB. and LiuT., Aspect level sentiment classification with deep memory network. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, (2016), pp. 214–224.
25.
ChenP., SunZ., BingL. and YangW., Recurrent attention network on memory for aspect sentiment analysis. In Proceedings of the 2017 conference on empirical methods in natural language processing, (2017), pp. 452–461.
26.
YinY., WeiF., DongL., XuK., ZhangM. and ZhouM., Unsupervised word and dependency path embeddings for aspect term extraction. In Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, (2016), pp. 2979–2985. AAAI Press.
27.
WangW., PanS.J., DahlmeierD. and XiaoX., Coupled multi-layer attentions for co-extraction of aspect and opinion terms. In Thirty-First AAAI Conference on Artificial Intelligence, 2017.
