{"type":"ScholarlyArticle","title":"Neural Subgraph Explorer: Reducing Noisy Information via Target-oriented Syntax Graph Pruning","authors":[{"name":"Bowen Xing","slug":"bowen-xing","given":"Bowen","family":"Xing","affiliation":"Australian Artificial Intelligence Institute , University of Technology Sydney , Australia"},{"name":"Ivor Tsang","slug":"ivor-tsang","given":"Ivor","family":"Tsang","affiliation":"Centre for Frontier AI Research , A*STAR , Singapore; Australian Artificial Intelligence Institute , University of Technology Sydney , Australia"}],"abstract":"Recent years have witnessed the emerging success of leveraging syntax graphs for the target sentiment classification task.\r\nHowever, we discover that existing syntax-based models suffer from two issues:\r\nnoisy information aggregation and loss of distant correlations.\r\nIn this paper, we propose a novel model termed Neural Subgraph Explorer, which \r\n(1) reduces the noisy information via pruning target-irrelevant nodes on the syntax graph;\r\n(2) introduces beneficial first-order connections between the target and its related words into the obtained graph.\r\nSpecifically, we design a multi-hop actions score estimator to evaluate the value of each word regarding the specific target.\r\nThe discrete action sequence is sampled through Gumble-Softmax and then used for both of the syntax graph and the self-attention graph.\r\nTo introduce the first-order connections between the target and its relevant words, the two pruned graphs are merged.\r\nFinally, graph convolution is conducted on the obtained unified graph to update the hidden states.\r\nAnd this process is stacked with multiple layers.\r\nTo our knowledge, this is the first attempt of target-oriented syntax graph pruning in this task.\r\nExperimental results demonstrate the superiority of our model, which achieves new state-of-the-art performance.","doi":"10.24963/ijcai.2022/614","url":"https://ijcai.org/proceedings/2022/614","pdf":"https://ijcai.org/proceedings/2022/0614.pdf","markdown":"https://ijcai.org/proceedings/2022/614.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/614","volume":{"slug":"2022","title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2022","url":"https://ijcai.org/proceedings/2022/","year":2022,"location":"Vienna","dates":"23-29 July 2022","editors":"Luc De Raedt","isbn":"978-1-956792-00-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2022"},"section":"Natural Language Processing","track":"Main Track","number":614,"pages":{"first":4425,"last":4431},"keywords":["Machine Learning: Sequence and Graph Learning","Natural Language Processing: Sentiment Analysis and Text Mining","Natural Language Processing: Text Classification"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38986517","length_sec":88,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38984660","length_sec":345,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Chen et al., 2017] Peng Chen, Zhongqian Sun, Lidong Bing, and Wei Yang. Recurrent attention network on mem- ory for aspect sentiment analysis. In EMNLP, pages 452- 461, 2017.","title":"Recurrent attention network on memory for aspect sentiment analysis","authors":"Peng Chen, Zhongqian Sun, Lidong Bing, Wei Yang","year":"2017","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Devlin et al., 2019] Jacob Devlin, Ming-Wei Chang, Ken- ton Lee, and Kristina Toutanova. BERT: Pre-training of deep bidirectional transformers for language understand- ing. In NAACL, pages 4171-4186, 2019.","title":"BERT: Pre-training of deep bidirectional transformers for language understanding","authors":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, Kristina Toutanova","year":"2019","venue":"NAACL","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Huang and Carley, 2019] Binxuan Huang and Kathleen Carley. Syntax-aware aspect level sentiment classification with graph attention networks. In EMNLP, pages 5469- 5477, Hong Kong, China, 2019.","title":"Syntax-aware aspect level sentiment classification with graph attention networks","authors":"Carley ; Huang, Binxuan Huang, Kathleen Carley","year":"2019","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Huang et al., 2020] Lianzhe Huang, Xin Sun, Sujian Li, Linhao Zhang, and Houfeng Wang. Syntax-aware graph attention network for aspect-level sentiment classification. In COLING, pages 799-810, 2020.","title":"Syntax-aware graph attention network for aspect-level sentiment classification","authors":"Huang","year":"2020","venue":"COLING","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Jang et al., 2017] Eric Jang, Shixiang Gu, and Ben Poole. Categorical reparameterization with gumbel-softmax. In ICLR (Poster), 2017.","title":"Categorical reparameterization with gumbel-softmax","authors":"Eric Jang, Shixiang Gu, Ben Poole","year":"2017","venue":"ICLR (Poster)","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Li et al., 2021] Ruifan Li, Hao Chen, Fangxiang Feng, Zhanyu Ma, Xiaojie Wang, and Eduard Hovy. Dual graph convolutional networks for aspect-based sentiment analy- sis. In ACL, pages 6319-6329, 2021.","title":"Dual graph convolutional networks for aspect-based sentiment analysis","authors":"Li","year":"2021","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Ma et al., 2017] Dehong Ma, Sujian Li, Xiaodong Zhang, and Houfeng Wang. Interactive attention networks for aspect-level sentiment classification. In IJCAI, pages 4068-4074, 2017.","title":"Interactive attention networks for aspect-level sentiment classification","authors":"Dehong Ma, Sujian Li, Xiaodong Zhang, Houfeng Wang","year":"2017","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2017/568"},{"position":8,"raw":"[Pontiki et al., 2014] Maria Pontiki, Dimitris Galanis, John Pavlopoulos, Harris Papageorgiou, Ion Androutsopoulos, and Suresh Manandhar. SemEval-2014 task 4: Aspect based sentiment analysis. In SemEval 2014, pages 27-35, 2014.","title":"SemEval-2014 task 4: Aspect based sentiment analysis","authors":"Maria Pontiki, Dimitris Galanis, John Pavlopoulos, Harris Papageorgiou, Ion Androutsopoulos, Suresh Manandhar","year":"2014","venue":"SemEval 2014","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Pontiki et al., 2015] Maria Pontiki, Dimitris Galanis, Haris Papageorgiou, Suresh Manandhar, and Ion Androutsopou- los. SemEval-2015 task 12: Aspect based sentiment anal- ysis. In SemEval 2015, pages 486-495, 2015.","title":"Androutsopoulos. SemEval-2015 task 12: Aspect based sentiment analysis","authors":"Maria Pontiki, Dimitris Galanis, Haris Papageorgiou, Suresh Manandhar, Ion","year":"2015","venue":"SemEval 2015","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Song et al., 2019] Youwei Song, Jiahai Wang, Tao Jiang, Zhiyue Liu, and Yanghui Rao. Attentional encoder net- work for targeted sentiment classification. arXiv preprint arXiv:1902.09314, 2019.","title":"Attentional encoder network for targeted sentiment classification","authors":"Youwei Song, Jiahai Wang, Tao Jiang, Zhiyue Liu, Yanghui Rao","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Tang et al., 2016] Duyu Tang, Bing Qin, Xiaocheng Feng, and Ting Liu. Effective LSTMs for target-dependent senti- ment classification. In COLING, pages 3298-3307, 2016.","title":"Effective LSTMs for target-dependent sentiment classification","authors":"Tang","year":"2016","venue":"COLING","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Tang et al., 2019] Jialong Tang, Ziyao Lu, Jinsong Su, Yu- bin Ge, Linfeng Song, Le Sun, and Jiebo Luo. Progres- sive self-supervised attention learning for aspect-level sen- timent analysis. In ACL, pages 557-566, 2019.","title":"Progressive self-supervised attention learning for aspect-level sentiment analysis","authors":"Jialong Tang, Ziyao Lu, Jinsong Su, Yubin Ge, Linfeng Song, Le Sun, Jiebo Luo","year":"2019","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Tang et al., 2020] Hao Tang, Donghong Ji, Chenliang Li, and Qiji Zhou. Dependency graph enhanced dual- transformer structure for aspect-based sentiment classifi- cation. In ACL, pages 6578-6588, 2020.","title":"Dependency graph enhanced dualtransformer structure for aspect-based sentiment classification","authors":"Hao Tang, Donghong Ji, Chenliang Li, Qiji Zhou","year":"2020","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Tian et al., 2021a] Yuanhe Tian, Guimin Chen, and Yan Song. Aspect-based sentiment analysis with type-aware graph convolutional networks and layer ensemble. In NAACL, pages 2910-2922, 2021.","title":"Aspect-based sentiment analysis with type-aware graph convolutional networks and layer ensemble","authors":"Tian","year":"2021","venue":"NAACL","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Tian et al., 2021b] Yuanhe Tian, Guimin Chen, and Yan Song. Enhancing aspect-level sentiment analysis with word dependencies. In EACL, pages 3726-3739, 2021.","title":"Enhancing aspect-level sentiment analysis with word dependencies","authors":"Tian","year":"2021","venue":"EACL","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Vaswani et al., 2017] Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. Attention is all you need. In NIPS, pages 5998-6008, 2017.","title":"Attention is all you need","authors":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, Illia Polosukhin","year":"2017","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Wang et al., 2016] Yequan Wang, Minlie Huang, Xiaoyan Zhu, and Li Zhao. Attention-based LSTM for aspect-level sentiment classification. In EMNLP, pages 606-615, 2016.","title":"Attention-based LSTM for aspect-level sentiment classification","authors":"Wang","year":"2016","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Wang et al., 2020] Kai Wang, Weizhou Shen, Yunyi Yang, Xiaojun Quan, and Rui Wang. Relational graph atten- tion network for aspect-based sentiment analysis. In ACL, pages 3229-3238, 2020.","title":"Relational graph attention network for aspect-based sentiment analysis","authors":"Kai Wang, Weizhou Shen, Yunyi Yang, Xiaojun Quan, Rui Wang","year":"2020","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Williams, 1992] Ronald J. Williams. Simple statistical gradient-following algorithms for connectionist reinforce- ment learning. Machine Learning, 8(3-4):229-256, 1992.","title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning","authors":"Ronald J Williams","year":"1992","venue":"Machine Learning","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Xing and Tsang, 2021] Bowen Xing and Ivor W Tsang. Out of context: A new clue for context modeling of aspect-based sentiment analysis. arXiv preprint arXiv:2106.10816, 2021.","title":"Out of context: A new clue for context modeling of aspect-based sentiment analysis","authors":"Tsang ; ] Xing, Xing Bowen, Ivor W Tsang","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Xing and Tsang, 2022a] Bowen Xing and Ivor Tsang. Dignet: Digging clues from local-global interactive graph for aspect-level sentiment classification. arXiv preprint arXiv:2201.00989, 2022.","title":"Dignet: Digging clues from local-global interactive graph for aspect-level sentiment classification","authors":"Tsang Xing, Bowen Xing, Ivor Tsang","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Xing and Tsang, 2022b] Bowen Xing and Ivor W. Tsang. Understand me, if you refer to aspect knowledge: Knowledge-aware gated recurrent memory network. IEEE Transactions on Emerging Topics in Computational Intel- ligence, pages 1-11, 2022.","title":"Understand me, if you refer to aspect knowledge: Knowledge-aware gated recurrent memory network","authors":"Tsang Xing, Bowen Xing, Ivor W Tsang","year":"2022","venue":"IEEE Transactions on Emerging Topics in Computational Intelligence","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Xing et al., 2019] Bowen Xing, Lejian Liao, Dandan Song, Jingang Wang, Fuzheng Zhang, Zhongyuan Wang, and Heyan Huang. Earlier attention? aspect-aware LSTM for aspect-based sentiment analysis. In IJCAI, pages 5313- 5319, 2019.","title":"Earlier attention? aspect-aware LSTM for aspect-based sentiment analysis","authors":"Lejian Bowen Xing, Dandan Liao, Jingang Song, Fuzheng Wang, Zhongyuan Zhang, Heyan Wang, Huang","year":"2019","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2019/738"},{"position":24,"raw":"[Zhang and Qian, 2020] Mi Zhang and Tieyun Qian. Con- volution over hierarchical syntactic and lexical graphs for aspect level sentiment analysis. In EMNLP, pages 3540- 3549, Online, 2020.","title":"Convolution over hierarchical syntactic and lexical graphs for aspect level sentiment analysis","authors":"Mi Zhang, Tieyun Qian","year":"2020","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Zhang et al., 2019] Chen Zhang, Qiuchi Li, and Dawei Song. Aspect-based sentiment classification with aspect- specific graph convolutional networks. In EMNLP, pages 4568-4578, 2019.","title":"Aspect-based sentiment classification with aspectspecific graph convolutional networks","authors":"Chen Zhang, Qiuchi Li, Dawei Song","year":"2019","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Zhang et al., 2020] Bowen Zhang, Xutao Li, Xiaofei Xu, Ka-Cheong Leung, Zhiyao Chen, and Yunming Ye. Knowledge guided capsule attention network for aspect- based sentiment analysis. IEEE ACM Trans. Audio Speech Lang. Process., 28:2538-2551, 2020.","title":"Knowledge guided capsule attention network for aspectbased sentiment analysis","authors":"Bowen Zhang, Xutao Li, Xiaofei Xu, Ka-Cheong Leung, Zhiyao Chen, Yunming Ye","year":"2020","venue":"IEEE ACM Trans. Audio Speech Lang. Process","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}