{"type":"ScholarlyArticle","title":"Learning Few-shot Sample-set Operations for Noisy Multi-label Aspect Category Detection","authors":[{"name":"Shiman Zhao","slug":"shiman-zhao","given":"Shiman","family":"Zhao","affiliation":""},{"name":"Wei Chen","slug":"wei-chen","given":"Wei","family":"Chen","affiliation":""},{"name":"Tengjiao Wang","slug":"tengjiao-wang","given":"Tengjiao","family":"Wang","affiliation":""}],"abstract":"Multi-label Aspect Category Detection (MACD) is essential for aspect-based sentiment analysis, which aims to identify multiple aspect categories in a given sentence. Few-shot MACD is critical due to the scarcity of labeled data. However, MACD is a high-noise task, and existing methods fail to address it with only two or three training samples per class, which limits the application in practice. To solve above issues, we propose a group of Few-shot Sample-set Operations (FSO) to solve noisy MACD in fewer sample scenarios by identifying the semantic contents of samples. Learning interactions among intersection, subtraction, and union networks, the FSO imitates arithmetic operations on samples to distinguish relevant and irrelevant aspect contents. Eliminating the negative effect caused by noises, the FSO extracts discriminative prototypes and customizes a dedicated query vector for each class. Besides, we design a multi-label architecture, which integrates with score-wise loss and multi-label loss to optimize the FSO for multi-label prediction, avoiding complex threshold training or selection. Experiments show that our method achieves considerable performance. Significantly, it improves by 11.01% at most and an average of 8.59% Macro-F in fewer sample scenarios.","doi":"10.24963/ijcai.2023/589","url":"https://ijcai.org/proceedings/2023/589","pdf":"https://ijcai.org/proceedings/2023/0589.pdf","markdown":"https://ijcai.org/proceedings/2023/589.md","bibtex":"https://ijcai.org/proceedings/2023/bibtex/589","volume":{"slug":"2023","title":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2023","url":"https://ijcai.org/proceedings/2023/","year":2023,"location":"Macao, SAR","dates":"19-25 August 2023","editors":"Edith Elkind","isbn":"978-1-956792-03-4","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2023"},"section":"Natural Language Processing","track":"Main Track","number":589,"pages":{"first":5306,"last":5313},"keywords":["Machine Learning: ML: Few-shot learning","Natural Language Processing: NLP: Dialogue and interactive systems","Natural Language Processing: NLP: Sentiment analysis, stylistic analysis, and argument mining"],"videos":[],"references":[{"position":1,"raw":"[Alfassy et al., 2019] Amit Alfassy, Leonid Karlinsky, Amit Aides, Joseph Shtok, Sivan Harary, Rogerio Feris, Raja Giryes, and Alex M Bronstein. Laso: Label-set opera- tions networks for multi-label few-shot learning. In Proc. of CVPR, pages 6548-6557, 2019.","title":"Laso: Label-set operations networks for multi-label few-shot learning","authors":"Amit Alfassy, Leonid Karlinsky, Amit Aides, Joseph Shtok, Sivan Harary, Rogerio Feris, Raja Giryes, Alex M Bronstein","year":"2019","venue":"Proc. of CVPR","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Allen et al., 2019] Kelsey Allen, Evan Shelhamer, Hanul Shin, and Joshua Tenenbaum. Infinite mixture prototypes for few-shot learning. In ICML, pages 232-241. PMLR, 2019.","title":"Infinite mixture prototypes for few-shot learning","authors":"Kelsey Allen, Evan Shelhamer, Hanul Shin, Joshua Tenenbaum","year":"2019","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Assran et al., 2022] Mahmoud Assran, Mathilde Caron, Is- han Misra, Piotr Bojanowski, Florian Bordes, Pascal Vin- cent, Armand Joulin, Mike Rabbat, and Nicolas Ballas. Masked siamese networks for label-efficient learning. In Proc. of ECCV, pages 456-473. Springer, 2022.","title":"Masked siamese networks for label-efficient learning","authors":"Mahmoud Assran, Mathilde Caron, Ishan Misra, Piotr Bojanowski, Florian Bordes, Pascal Vincent, Armand Joulin, Mike Rabbat, Nicolas Ballas","year":"2022","venue":"Proc. of ECCV","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Bauman et al., 2017] Konstantin Bauman, Bing Liu, and Alexander Tuzhilin. Aspect based recommendations: Rec- ommending items with the most valuable aspects based on user reviews. In Proc. of ACM SIGKDD, pages 717-725, 2017.","title":"Aspect based recommendations: Recommending items with the most valuable aspects based on user reviews","authors":"Konstantin Bauman, Bing Liu, Alexander Tuzhilin","year":"2017","venue":"Proc. of ACM SIGKDD","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Cai et al., 2020] Hongjie Cai, Yaofeng Tu, Xiangsheng Zhou, Jianfei Yu, and Rui Xia. Aspect-category based sentiment analysis with hierarchical graph convolutional network. In Proc. of ICCL, pages 833-843, 2020.","title":"Aspect-category based sentiment analysis with hierarchical graph convolutional network","authors":"Hongjie Cai, Yaofeng Tu, Xiangsheng Zhou, Jianfei Yu, Rui Xia","year":"2020","venue":"Proc. of ICCL","doi":null,"url":null,"internal_url":null},{"position":6,"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 Proc. of NAACL-HLT, 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":"Proc. of NAACL-HLT","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Gao et al., 2019] Tianyu Gao, Xu Han, Zhiyuan Liu, and Maosong Sun. Hybrid attention-based prototypical net- works for noisy few-shot relation classification. In Proc. of AAAI, volume 33, pages 6407-6414, 2019.","title":"Hybrid attention-based prototypical networks for noisy few-shot relation classification","authors":"Tianyu Gao, Xu Han, Zhiyuan Liu, Maosong Sun","year":"2019","venue":"Proc. of AAAI","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Hospedales et al., 2021] Timothy Hospedales, Antreas An- toniou, Paul Micaelli, and Amos Storkey. Meta-learning in neural networks: A survey. IEEE Trans. Pattern Anal. Mach. Intell., 44(9):5149-5169, 2021.","title":"Meta-learning in neural networks: A survey","authors":"Hospedales","year":"2021","venue":"IEEE Trans. Pattern Anal. Mach. Intell","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Hu et al., 2021] Mengting Hu, Shiwan Zhao, Honglei Guo, Chao Xue, Hang Gao, Tiegang Gao, Renhong Cheng, and Zhong Su. Multi-label few-shot learning for aspect cate- gory detection. In Proc. of ACL, 2021.","title":"Multi-label few-shot learning for aspect category detection","authors":"Mengting Hu, Shiwan Zhao, Honglei Guo, Chao Xue, Hang Gao, Tiegang Gao, Renhong Cheng, Zhong Su","year":"2021","venue":"Proc. of ACL","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Laurens and Hinton, 2008] Van Der Maaten Laurens and Geoffrey Hinton. Visualizing data using t-sne. Journal of Machine Learning Research, 9(2605):2579-2605, 2008.","title":"Visualizing data using t-sne","authors":"Laurens, Hinton, Van Der, Maaten Laurens, Geoffrey Hinton","year":"2008","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Lee et al., 2019] Kwonjoon Lee, Subhransu Maji, Avinash Ravichandran, and Stefano Soatto. Meta-learning with dif- ferentiable convex optimization. In Proc. of CVPR, pages 10657-10665, 2019.","title":"Meta-learning with differentiable convex optimization","authors":"Lee","year":"2019","venue":"Proc. of CVPR","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Li et al., 2020] Yuncong Li, Cunxiang Yin, Sheng-hua Zhong, and Xu Pan. Multi-instance multi-label learning networks for aspect-category sentiment analysis. In Proc. of EMNLP, pages 3550-3560, 2020.","title":"Multi-instance multi-label learning networks for aspect-category sentiment analysis","authors":"Li","year":"2020","venue":"Proc. of EMNLP","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Liu et al., 2022] Han Liu, Feng Zhang, Xiaotong Zhang, Siyang Zhao, Junjie Sun, Hong Yu, and Xianchao Zhang. Label-enhanced prototypical network with contrastive learning for multi-label few-shot aspect category detec- tion. In Proc. of ACM SIGKDD, pages 1079-1087, 2022.","title":"Label-enhanced prototypical network with contrastive learning for multi-label few-shot aspect category detection","authors":"Han Liu, Feng Zhang, Xiaotong Zhang, Siyang Zhao, Junjie Sun, Hong Yu, Xianchao Zhang","year":"2022","venue":"Proc. of ACM SIGKDD","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Lv et al., 2021] Hui Lv, Chen Chen, Zhen Cui, Chunyan Xu, Yong Li, and Jian Yang. Learning normal dynamics in videos with meta prototype network. In Proc. of CVPR, pages 15425-15434, 2021.","title":"Learning normal dynamics in videos with meta prototype network","authors":"Hui Lv, Chen Chen, Zhen Cui, Chunyan Xu, Yong Li, Jian Yang","year":"2021","venue":"Proc. of CVPR","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Pontiki et al., 2016] Maria Pontiki, Dimitris Galanis, Haris Papageorgiou, Ion Androutsopoulos, and Manandhar. Semeval-2016 task 5: Aspect based sentiment analysis. In Proc. of SemEval 2016, pages 19-30, 01 2016.","title":"Semeval-2016 task 5: Aspect based sentiment analysis","authors":"Maria Pontiki, Dimitris Galanis, Haris Papageorgiou, Ion Androutsopoulos, Manandhar","year":"2016","venue":"Proc. of SemEval 2016","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Schmitt et al., 2018] Martin Schmitt, Simon Steinheber, Konrad Schreiber, and Benjamin Roth. Joint aspect and polarity classification for aspect-based sentiment analysis with end-to-end neural networks. In Proc. of EMNLP, 2018.","title":"Joint aspect and polarity classification for aspect-based sentiment analysis with end-to-end neural networks","authors":"Martin Schmitt, Simon Steinheber, Konrad Schreiber, Benjamin Roth","year":"2018","venue":"Proc. of EMNLP","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Snell et al., 2017] Jake Snell, Kevin Swersky, and Richard Zemel. Prototypical networks for few-shot learning. In NeurIPS, volume 30, 2017.","title":"Prototypical networks for few-shot learning","authors":"Jake Snell, Kevin Swersky, Richard Zemel","year":"2017","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Sun et al., 2020] Yifan Sun, Changmao Cheng, Yuhan Zhang, Chi Zhang, Liang Zheng, Zhongdao Wang, and Yichen Wei. Circle loss: A unified perspective of pair sim- ilarity optimization. In Proc. of CVPR, pages 6398-6407, 2020.","title":"Circle loss: A unified perspective of pair similarity optimization","authors":"Yifan Sun, Changmao Cheng, Yuhan Zhang, Chi Zhang, Liang Zheng, Zhongdao Wang, Yichen Wei","year":"2020","venue":"Proc. of CVPR","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Sung et al., 2018] Flood Sung, Yongxin Yang, Li Zhang, Tao Xiang, Philip HS Torr, and Timothy M Hospedales. Learning to compare: Relation network for few-shot learn- ing. In Proc. of CVPR, pages 1199-1208, 2018.","title":"Learning to compare: Relation network for few-shot learning","authors":"Sung","year":"2018","venue":"Proc. of CVPR","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Tsendsuren and Hong, 2017] Munkhdalai Tsendsuren and Yu Hong. Meta networks. In Proc. of ICML, pages 2554- 2563, 2017.","title":"Munkhdalai Tsendsuren and Yu Hong. Meta networks","authors":"Hong Tsendsuren","year":"2017","venue":"Proc. of ICML","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Tulkens et al., 2020] Tulkens, Cranenburgh, and andAn- dreas. Embarrassingly simple unsupervised aspect extrac- tion. In Proc. of ACL, 2020.","title":"Tulkens, Cranenburgh, and andAndreas. Embarrassingly simple unsupervised aspect extraction","authors":"Tulkens","year":"2020","venue":"Proc. of ACL","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Wang et al., 2021] Runzhong Wang, Junchi Yan, and Xi- aokang Yang. Neural graph matching network: Learn- ing lawler's quadratic assignment problem with extension to hypergraph and multiple-graph matching. IEEE Trans. Pattern Anal. Mach. Intell., 2021.","title":"Neural graph matching network: Learning lawler's quadratic assignment problem with extension to hypergraph and multiple-graph matching","authors":"Wang","year":"2021","venue":"IEEE Trans. Pattern Anal. Mach. Intell","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Yan et al., 2022] Kun Yan, Chenbin Zhang, Jun Hou, Ping Wang, Zied Bouraoui, Shoaib Jameel, and Steven Schock- aert. Inferring prototypes for multi-label few-shot image classification with word vector guided attention. In Proc. of AAAI, 2022.","title":"Inferring prototypes for multi-label few-shot image classification with word vector guided attention","authors":"Kun Yan, Chenbin Zhang, Jun Hou, Ping Wang, Zied Bouraoui, Shoaib Jameel, Steven Schockaert","year":"2022","venue":"Proc. of AAAI","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Yang et al., 2020] Zhuo Yang, Yufei Han, Guoxian Yu, Qiang Yang, and Xiangliang Zhang. Prototypical networks for multi-label learning. In Proc. of AAAI, 2020.","title":"Prototypical networks for multi-label learning","authors":"Zhuo Yang, Yufei Han, Guoxian Yu, Qiang Yang, Xiangliang Zhang","year":"2020","venue":"Proc. of AAAI","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Yu et al., 2021] Weiping Yu, Taojiannan Yang, and Chen Chen. Towards resolving the challenge of long-tail dis- tribution in uav images for object detection. In Proc. of WACV, pages 3258-3267, January 2021.","title":"Towards resolving the challenge of long-tail distribution in uav images for object detection","authors":"Weiping Yu, Taojiannan Yang, Chen Chen","year":"2021","venue":"Proc. of WACV","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Zhao et al., 2022] Fei Zhao, Yuchen Shen, Zhen Wu, and Xinyu Dai. Label-driven denoising framework for multi- label few-shot aspect category detection. Findings of EMNLP, 2022.","title":"Label-driven denoising framework for multilabel few-shot aspect category detection","authors":"Fei Zhao, Yuchen Shen, Zhen Wu, Xinyu Dai","year":"2022","venue":"Findings of EMNLP","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}