{"type":"ScholarlyArticle","title":"Inheriting the Wisdom of Predecessors: A Multiplex Cascade Framework for Unified Aspect-based Sentiment Analysis","authors":[{"name":"Hao Fei","slug":"hao-fei","given":"Hao","family":"Fei","affiliation":"Key Laboratory of Aerospace Information Security and Trusted Computing , Ministry of Education , School of Cyber Science and Engineering , Wuhan University , China"},{"name":"Fei Li","slug":"fei-li","given":"Fei","family":"Li","affiliation":"Key Laboratory of Aerospace Information Security and Trusted Computing , Ministry of Education , School of Cyber Science and Engineering , Wuhan University , China"},{"name":"Chenliang Li","slug":"chenliang-li","given":"Chenliang","family":"Li","affiliation":"Key Laboratory of Aerospace Information Security and Trusted Computing , Ministry of Education , School of Cyber Science and Engineering , Wuhan University , China"},{"name":"Shengqiong Wu","slug":"shengqiong-wu","given":"Shengqiong","family":"Wu","affiliation":"Key Laboratory of Aerospace Information Security and Trusted Computing , Ministry of Education , School of Cyber Science and Engineering , Wuhan University , China"},{"name":"Jingye Li","slug":"jingye-li","given":"Jingye","family":"Li","affiliation":"Key Laboratory of Aerospace Information Security and Trusted Computing , Ministry of Education , School of Cyber Science and Engineering , Wuhan University , China"},{"name":"Donghong Ji","slug":"donghong-ji","given":"Donghong","family":"Ji","affiliation":"Key Laboratory of Aerospace Information Security and Trusted Computing , Ministry of Education , School of Cyber Science and Engineering , Wuhan University , China"}],"abstract":"So far, aspect-based sentiment analysis (ABSA) has involved with total seven subtasks, in which, however the interactions among them have been left unexplored sufficiently. This work presents a novel multiplex cascade framework for unified ABSA and maintaining such interactions. First, we model total seven subtasks as a hierarchical dependency in the easy-to-hard order, based on which we then propose a multiplex decoding mechanism, transferring the sentiment layouts and clues in lower tasks to upper ones. The multiplex strategy enables highly-efficient subtask interflows and avoids repetitive training; meanwhile it sufficiently utilizes the existing data without requiring any further annotation. Further, based on the characteristics of aspect-opinion term extraction and pairing, we enhance our multiplex framework by integrating POS tag and syntactic dependency information for term boundary and pairing identification. The proposed Syntax-aware Multiplex (SyMux) framework enhances the ABSA performances on 28 subtasks (7×4 datasets) with big margins.","doi":"10.24963/ijcai.2022/572","url":"https://ijcai.org/proceedings/2022/572","pdf":"https://ijcai.org/proceedings/2022/0572.pdf","markdown":"https://ijcai.org/proceedings/2022/572.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/572","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":572,"pages":{"first":4121,"last":4128},"keywords":["Natural Language Processing: Information Extraction","Natural Language Processing: Text Classification","Natural Language Processing: Sentiment Analysis and Text Mining"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38986790","length_sec":83,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38984933","length_sec":342,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Chen and Qian, 2020] Zhuang Chen and Tieyun Qian. Relation-aware collaborative learning for unified aspect- based sentiment analysis. In ACL, pages 3685-3694, 2020.","title":"Relation-aware collaborative learning for unified aspectbased sentiment analysis","authors":"Zhuang Chen, Tieyun Qian","year":"2020","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Chen et al., 2020] Peng Chen, Shaowei Chen, and Jie Liu. Hierarchical sequence labeling model for aspect sentiment triplet extraction. In NLPCC, pages 654-666, 2020.","title":"Hierarchical sequence labeling model for aspect sentiment triplet extraction","authors":"Peng Chen, Shaowei Chen, Jie Liu","year":"2020","venue":"NLPCC","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Dai and Song, 2019] Hongliang Dai and Yangqiu Song. Neural aspect and opinion term extraction with mined rules as weak supervision. In ACL, pages 5268-5277, 2019.","title":"Neural aspect and opinion term extraction with mined rules as weak supervision","authors":"Song ; Dai, Hongliang Dai, Yangqiu Song","year":"2019","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":4,"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":5,"raw":"[Eberts and Ulges, 2020] Markus Eberts and Adrian Ulges. Span-based joint entity and relation extraction with trans- former pre-training. In ECAI, pages 2006-2013, 2020.","title":"Span-based joint entity and relation extraction with transformer pre-training","authors":"Ulges Eberts, Markus Eberts, Adrian Ulges","year":"2020","venue":"ECAI","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Fan et al., 2018] Feifan Fan, Yansong Feng, and Dongyan Zhao. Multi-grained attention network for aspect-level sentiment classification. In EMNLP, pages 3433-3442, 2018.","title":"Multi-grained attention network for aspect-level sentiment classification","authors":"Fan","year":"2018","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Fan et al., 2019] Zhifang Fan, Zhen Wu, Xin-Yu Dai, Shu- jian Huang, and Jiajun Chen. Target-oriented opinion words extraction with target-fused neural sequence label- ing. In NAACL, pages 2509-2518, 2019.","title":"Target-oriented opinion words extraction with target-fused neural sequence labeling","authors":"Zhifang Fan, Zhen Wu, Xin-Yu Dai, Shujian Huang, Jiajun Chen","year":"2019","venue":"NAACL","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Fei et al., 2020] Hao Fei, Yafeng Ren, and Donghong Ji. Retrofitting structure-aware transformer language model for end tasks. In EMNLP, pages 2151-2161, 2020.","title":"Retrofitting structure-aware transformer language model for end tasks","authors":"Yafeng Hao Fei, Donghong Ren, Ji","year":"2020","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Fei et al., 2021a] Hao Fei, Fei Li, Bobo Li, and Donghong Ji. Encoder-decoder based unified semantic role labeling with label-aware syntax. In AAAI, pages 12794-12802, 2021.","title":"Encoder-decoder based unified semantic role labeling with label-aware syntax","authors":"Fei","year":"2021","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Fei et al., 2021b] Hao Fei, Yafeng Ren, Shengqiong Wu, Bobo Li, and Donghong Ji. Latent target-opinion as prior for document-level sentiment classification: A variational approach from fine-grained perspective. In Proceedings of the WWW: the Web Conference, pages 553-564, 2021.","title":"Latent target-opinion as prior for document-level sentiment classification: A variational approach from fine-grained perspective","authors":"Fei","year":"2021","venue":"Proceedings of the WWW: the Web Conference","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Fei et al., 2021c] Hao Fei, Shengqiong Wu, Yafeng Ren, Fei Li, and Donghong Ji. Better combine them together! integrating syntactic constituency and dependency repre- sentations for semantic role labeling. In Findings of the Association for Computational Linguistics: ACL/IJCNLP 2021, pages 549-559, 2021.","title":"Better combine them together! integrating syntactic constituency and dependency representations for semantic role labeling","authors":"Fei","year":"2021","venue":"Findings of the Association for Computational Linguistics: ACL/IJCNLP 2021","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[He et al., 2019] Ruidan He, Wee Sun Lee, Hwee Tou Ng, and Daniel Dahlmeier. An interactive multi-task learning network for end-to-end aspect-based sentiment analysis. In ACL, pages 504-515, 2019.","title":"An interactive multi-task learning network for end-to-end aspect-based sentiment analysis","authors":"He","year":"2019","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Hu et al., 2019] Minghao Hu, Yuxing Peng, Zhen Huang, Dongsheng Li, and Yiwei Lv. Open-domain targeted senti- ment analysis via span-based extraction and classification. In ACL, pages 537-546, 2019.","title":"Open-domain targeted sentiment analysis via span-based extraction and classification","authors":"Minghao Hu, Yuxing Peng, Zhen Huang, Dongsheng Li, Yiwei Lv","year":"2019","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":14,"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, 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":15,"raw":"[Li and Lam, 2017] Xin Li and Wai Lam. Deep multi-task learning for aspect term extraction with memory interac- tion. In EMNLP, pages 2886-2892, 2017.","title":"Deep multi-task learning for aspect term extraction with memory interaction","authors":"Li, Lam ; ] Xin Li, Wai Lam","year":"2017","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Li et al., 2018] Xin Li, Lidong Bing, Wai Lam, and Bei Shi. Transformation networks for target-oriented senti- ment classification. In ACL, pages 946-956, 2018.","title":"Transformation networks for target-oriented sentiment classification","authors":"Xin Li, Lidong Bing, Wai Lam, Bei Shi","year":"2018","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Li et al., 2019] Xin Li, Lidong Bing, Piji Li, and Wai Lam. A unified model for opinion target extraction and target sentiment prediction. In AAAI, pages 6714-6721, 2019.","title":"A unified model for opinion target extraction and target sentiment prediction","authors":"Li","year":"2019","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Mao et al., 2021] Yue Mao, Yi Shen, Chao Yu, and Longjun Cai. A joint training dual-mrc framework for aspect based sentiment analysis. In AAAI, pages 13543-13551, 2021.","title":"A joint training dual-mrc framework for aspect based sentiment analysis","authors":"Yue Mao, Yi Shen, Chao Yu, Longjun Cai","year":"2021","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Peng et al., 2020] Haiyun Peng, Lu Xu, Lidong Bing, Fei Huang, Wei Lu, and Luo Si. Knowing what, how and why: A near complete solution for aspect-based sentiment anal- ysis. In AAAI, pages 8600-8607, 2020.","title":"Knowing what, how and why: A near complete solution for aspect-based sentiment analysis","authors":"Haiyun Peng, Lu Xu, Lidong Bing, Fei Huang, Wei Lu, Luo Si","year":"2020","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":20,"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, 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","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Pontiki et al., 2015] Maria Pontiki, Dimitrios Galanis, Suresh Manandhar, and Ion Androutsopoulos. Semeval- 2015 task 12: Aspect based sentiment analysis. In SemEval, pages 486-495, 2015.","title":"Semeval-2015 task 12: Aspect based sentiment analysis","authors":"Maria Pontiki, Dimitrios Galanis, Suresh Manandhar, Ion Androutsopoulos","year":"2015","venue":"SemEval","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Pontiki et al., 2016] Maria Pontiki, Salud María Jiménez- Zafra, and Güls ¸en Eryigit. SemEval-2016 task 5: Aspect based sentiment analysis. In SemEval, pages 19-30, 2016.","title":"SemEval-2016 task 5: Aspect based sentiment analysis","authors":"Maria Pontiki, Salud María Jiménez-Zafra, Güls ¸en Eryigit","year":"2016","venue":"SemEval","doi":null,"url":null,"internal_url":null},{"position":23,"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":24,"raw":"[Wang et al., 2017] Wenya Wang, Sinno Jialin Pan, Daniel Dahlmeier, and Xiaokui Xiao. Coupled multi-layer at- tentions for co-extraction of aspect and opinion terms. In AAAI, pages 3316-3322, 2017.","title":"Coupled multi-layer attentions for co-extraction of aspect and opinion terms","authors":"Wenya Wang, Sinno Jialin Pan, Daniel Dahlmeier, Xiaokui Xiao","year":"2017","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Wei et al., 2020] Zhepei Wei, Jianlin Su, Yue Wang, Yuan Tian, and Yi Chang. A novel cascade binary tagging framework for relational triple extraction. In ACL, pages 1476-1488, 2020.","title":"A novel cascade binary tagging framework for relational triple extraction","authors":"Zhepei Wei, Jianlin Su, Yue Wang, Yuan Tian, Yi Chang","year":"2020","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Wu et al., 2020] Zhen Wu, Chengcan Ying, Fei Zhao, Zhi- fang Fan, Xinyu Dai, and Rui Xia. Grid tagging scheme for aspect-oriented fine-grained opinion extraction. In Findings of the EMNLP, pages 2576-2585, 2020.","title":"Grid tagging scheme for aspect-oriented fine-grained opinion extraction","authors":"Zhen Wu, Chengcan Ying, Fei Zhao, Zhifang Fan, Xinyu Dai, Rui Xia","year":"2020","venue":"Findings of the EMNLP","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Wu et al., 2021] Shengqiong Wu, Hao Fei, Yafeng Ren, Donghong Ji, and Jingye Li. Learn from syntax: Improv- ing pair-wise aspect and opinion terms extraction with rich syntactic knowledge. In IJCAI, pages 3957-3963, 2021.","title":"Learn from syntax: Improving pair-wise aspect and opinion terms extraction with rich syntactic knowledge","authors":"Shengqiong Wu, Hao Fei, Yafeng Ren, Donghong Ji, Jingye Li","year":"2021","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2021/545"},{"position":28,"raw":"[Yan et al., 2021] Hang Yan, Junqi Dai, Tuo Ji, Xipeng Qiu, and Zheng Zhang. A unified generative framework for aspect-based sentiment analysis. In ACL, pages 2416- 2429, 2021.","title":"A unified generative framework for aspect-based sentiment analysis","authors":"Hang Yan, Junqi Dai, Tuo Ji, Xipeng Qiu, Zheng Zhang","year":"2021","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Yu et al., 2021] Guoxin Yu, Xiang Ao, Ling Luo, Min Yang, Xiaofei Sun, Jiwei Li, and Qing He. Making flexi- ble use of sub-tasks: A multiplex interaction network for unified aspect-based sentiment analysis. In Findings of the ACL, pages 2695-2705, 2021.","title":"Making flexible use of sub-tasks: A multiplex interaction network for unified aspect-based sentiment analysis","authors":"Guoxin Yu, Xiang Ao, Ling Luo, Min Yang, Xiaofei Sun, Jiwei Li, Qing He","year":"2021","venue":"Findings of the ACL","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Zhao et al., 2020] He Zhao, Longtao Huang, Rong Zhang, Quan Lu, and Hui Xue. Spanmlt: A span-based multi-task learning framework for pair-wise aspect and opinion terms extraction. In ACL, pages 3239-3248, 2020.","title":"Spanmlt: A span-based multi-task learning framework for pair-wise aspect and opinion terms extraction","authors":"Zhao","year":"2020","venue":"ACL","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}