少样本关系分类综述

doi:10.3778/j.issn.1002-8331.2208-0027

摘要/Abstract

摘要： 少样本关系分类旨在通过少量的有标注训练样本，来挖掘自然语言文本中目标实体之间所蕴含的语义关系，以应对传统的关系分类方法所面临的资源匮乏问题，从而能够较好地推广到医学、金融以及民语处理等数据稀缺的特定领域。目前，少样本关系分类的相关研究工作均在元学习的训练策略下学习先验知识，并以此快速适应新的任务，其大体上可以划分为基于原型网络、基于预训练语言模型、基于参数优化以及基于图神经网络四种方式。回顾少样本关系分类的发展，对不同研究方法的优势和局限性进行深入剖析和总结，在此基础上，分析该领域当前所面临的棘手问题和挑战，并进一步对其未来的研究方向进行展望。

关键词: 关系分类, 少样本学习, 度量学习, 元学习

Abstract: Few-shot relation classification aims to mine the semantic relationship between target entities in natural language texts with limited labeled training examples, so as to deal with the resource shortage problem faced by the traditional relation classification methods, so that it can be better applied to medicine, finance and ethnic language processing and other data scarce fields. At present, the relevant research work on few-shot relation classification all learns prior knowledge under the training strategy of meta learning, and to quickly adapt to new tasks. Generally, it can be divided into four classes method：prototype network based, pre-training language model based, parameter optimization based, and graph neural network based. This paper reviews the development of few-shot relation classification, analyzes and summarizes the advantages and limitations of different research methods. On this basis, the paper analyzes the current problems and challenge faced by few-shot relation classification, and prospects the future research directions of this field.

Key words: relation classification, few-shot learning, metric learning, meta learning

刘涛, 柯尊旺, 吾守尔·斯拉木. 少样本关系分类综述[J]. 计算机工程与应用, 2023, 59(9): 1-12.

LIU Tao, KE Zunwang, Wushour·Silamu. Survey of Few-Shot Relation Classification[J]. Computer Engineering and Applications, 2023, 59(9): 1-12.

参考文献

[1] 代建华，彭若瑶，许路，等.基于深度神经网络的信息抽取研究综述[J].西南师范大学学报（自然科学版），2022，47（4）：1-11.
DAI J H，PENG R Y，XU L，et al.A survey of information extraction based on deep neural networks[J].Journal of Southwest China Normal University（Natural Science Edition），2022，47（4）：1-11.
[2] 鄂海红，张文静，肖思琪，等.深度学习实体关系抽取研究综述[J].软件学报，2019，30（6）：1793-1818.
E H H，ZHANG W J，XIAO S Q，et al.Survey of entity relationship extraction based on deep learning[J].Journal of Software，2019，30（6）：1793-1818.
[3] KAMBHATLA N.Combining lexical，syntactic，and semantic features with maximum entropy models for information extraction[C]//Proceedings of the ACL Interactive Poster and Demonstration Sessions，2004：178-181.
[4] NGUYEN T V T，MOSCHITTI A，RICCARDI G.Convolution kernels on constituent，dependency and sequential structures for relation extraction[C]//Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing，2009：1378-1387.
[5] ZHOU G，ZHANG M，JI D，et al.Tree kernel-based relation extraction with context-sensitive structured parse tree information[C]//Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning（EMNLP-CoNLL），2007：728-736.
[6] CULOTTA A，SORENSEN J.Dependency tree kernels for relation extraction[C]//Proceedings of the 42nd Annual meeting of the Association for Computational Linguistics（ACL-04），2004：423-429.
[7] XIAO M，LIU C.Semantic relation classification via hierarchical recurrent neural network with attention[C]//Proceedings of COLING 2016，the 26th International Conference on Computational Linguistics：Technical Papers，2016：1254-1263.
[8] ZENG D，LIU K，LAI S，et al.Relation classification via convolutional deep neural network[C]//Proceedings of COLING 2014，the 25th International Conference on Computational Linguistics：Technical Papers，2014：2335-2344.
[9] ZHU H，LIN Y，LIU Z，et al.Graph neural networks with generated parameters for relation extraction[J].arXiv：1902. 00756，2019.
[10] MINTZ M，BILLS S，SNOW R，et al.Distant supervision for relation extraction without labeled data[C]//Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP，2009：1003-1011.
[11] JIANG X，WANG Q，LI P，et al.Relation extraction with multi-instance multi-label convolutional neural networks[C]//Proceedings of COLING 2016，the 26th International Conference on Computational Linguistics：Technical Papers，2016：1471-1480.
[12] LIN Y，SHEN S，LIU Z，et al.Neural relation extraction with selective attention over instances[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics（Volume 1：Long Papers），2016：2124-2133.
[13] YANG K，HE L，DAI X，et al.Exploiting noisy data in distant supervision relation classification[C]//Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics：Human Language Technologies（Volume 1：Long and Short Papers），2019：3216-3225.
[14] HOSPEDALES T，ANTONIOU A，MICAELLI P，et al.Meta-learning in neural networks：a survey[J].arXiv：2004.05439，2020.
[15] CHEN W Y，LIU Y C，KIRA Z，et al.A closer look at few-shot classification[J].arXiv：1904.04232，2019.
[16] SUN Q，LIU Y，CHUA T S，et al.Meta-transfer learning for few-shot learning[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2019：403-412.
[17] KARLINSKY L，SHTOK J，HARARY S，et al.Repmet：representative-based metric learning for classification and few-shot object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2019：5197-5206.
[18] KUMAR V，GLAUDE H，DE LICHY C，et al.A closer look at feature space data augmentation for few-shot intent classification[J].arXiv：1910.04176，2019.
[19] WANG B，WANG D.Plant leaves classification：a few-shot learning method based on siamese network[J].IEEE Access，2019，7：151754-151763.
[20] YANG H，HE X，PORIKLI F.One-shot action localization by learning sequence matching network[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2018：1450-1459.
[21] SNELL J，SWERSKY K，ZEMEL R.Prototypical networks for few-shot learning[C]//Advances in Neural Information Processing Systems，2017：1-11.
[22] HAN X，ZHU H，YU P，et al.FewRel：a large-scale supervised few-shot relation classification dataset with state-of-the-art evaluation[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing，2018：4803-4809.
[23] YE Z X，LING Z H.Multi-level matching and aggregation network for few-shot relation classification[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics，2019：2872-2881.
[24] GAO T，HAN X，LIU Z，et al.Hybrid attention-based prototypical networks for noisy few-shot relation classification[C]//Proceedings of the AAAI Conference on Artificial Intelligence，2019：6407-6414.
[25] SUN S，SUN Q，ZHOU K，et al.Hierarchical attention prototypical networks for few-shot text classification[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing（EMNLP-IJCNLP），2019：476-485.
[26] XIE Y，XU H，YANG C，et al.Multi-channel convo-lutional neural networks with adversarial training for few-shot relation classification（student abstract）[C]//Proceedings of the AAAI Conference on Artificial Intelligence，2020：13967-13968.
[27] FAN M，BAI Y，SUN M，et al.Large margin prototypical network for few-shot relation classification with fine-grained features[C]//Proceedings of the 28th ACM International Conference on Information and Knowledge Management，2019：2353-2356.
[28] REN H，CAI Y，CHEN X，et al.A two-phase prototypical network model for incremental few-shot relation classification[C]//Proceedings of the 28th International Conference on Computational Linguistics，2020：1618-1629.
[29] HAN J，CHENG B，LU W.Exploring task difficulty for few-shot relation extraction[C]//Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing，2021：2605-2616.
[30] DING N，WANG X，FU Y，et al.Prototypical represen-tation learning for relation extraction[J].arXiv：2103. 11647，2021.
[31] WANG Y，BAO J，LIU G，et al.Learning to decouple relations：few-shot relation classification with entity-guided attention and confusion-aware training[C]//Proceedings of the 28th International Conference on Computational Linguistics，2020：5799-5809.
[32] YANG K，ZHENG N，DAI X，et al.Enhance prototypical network with text descriptions for few-shot relation classification[C]//Proceedings of the 29th ACM International Conference on Information & Knowledge Management，2020：2273-2276.
[33] VRANDE?I? D.Wikidata：a new platform for collaborative data collection[C]//Proceedings of the 21st International Conference on World Wide Web，2012：1063-1064.
[34] YANG S，ZHANG Y，NIU G，et al.Entity concept-enhanced few-shot relation extraction[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing（Volume 2：Short Papers），2021：987-991.
[35] MIKOLOV T，CHEN K，CORRADO G，et al.Efficient estimation of word representations in vector space[J].arXiv：1301.3781，2013.
[36] CUCERZAN S.Large-scale named entity disambiguation based on Wikipedia data[C]//Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning（EMNLP-CoNLL），2007：708-716.
[37] ZHANG J，ZHU J，YANG Y，et al.Knowledge-enhanced domain adaptation in few-shot relation classification[C]//Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining，2021：2183-2191.
[38] GAO T，HAN X，ZHU H，et al.FewRel 2.0：towards more challenging few-shot relation classification[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing（EMNLP-IJCNLP），2019：6250-6255.
[39] 刘峤，李杨，段宏，等.知识图谱构建技术综述[J].计算机研究与发展，2016，53（3）：582-600.
LIU J，LI Y，DUAN H，et al，Knowledge graph constr-uction techiques[J].Journal of Computer Research and Development，2016，53（3）：582-600.
[40] DEVLIN J，CHANG M W，LEE K，et al.Bert：pretraining of deep bidirectional transformers for language understanding[J].arXiv：1810.04805，2018.
[41] FLORIDI L，CHIRIATTI M.GPT-3：its nature，scope，limits，and consequences[J].Minds and Machines，2020，30（4）：681-694.
[42] SOARES L B，FITZGERALD N，LING J，et al.Matching the blanks：distributional similarity for relation learning[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics，2019：2895-2905.
[43] PENG H，GAO T，HAN X，et al.Learning from Context or names? an empirical study on neural relation extraction[C]//Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing（EMNLP），2020：3661-3672.
[44] LIU Y，HU J，WAN X，et al.A simple yet effective relation information guided approach for few-shot relation extraction[C]//Findings of the Association for Computational Linguistics，2022：757-763.
[45] HAN J，CHENG B，NAN G.Learning discriminative and unbiased representations for few-shot relation extraction[C]//Proceedings of the 30th ACM International Conference on Information & Knowledge Management，2021：638-648.
[46] DONG M，PAN C，LUO Z.MapRE：an effective semantic mapping approach for low-resource relation extraction[C]//Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing，2021：2694-2704.
[47] FINN C，ABBEEL P，LEVINE S.Model-agnostic meta-learning for fast adaptation of deep networks[C]//Intern-ational Conference on Machine Learning，2017：1126-1135.
[48] DONG B，YAO Y，XIE R，et al.Meta-information guided meta-learning for few-shot relation classification[C]//Proceedings of the 28th International Conference on Computational Linguistics，2020：1594-1605.
[49] QU M，GAO T，XHONNEUX L P，et al.Few-shot relation extraction via bayesian meta-learning on relation graphs[C]//International Conference on Machine Learning，2020：7867-7876.
[50] WU Z，PAN S，CHEN F，et al.A comprehensive survey on graph neural networks[J].IEEE Transactions on Neural Networks and Learning Systems，2020，32（1）：4-24.
[51] GARCIA V，BRUNA J.Few-shot learning with graph neural networks[J].arXiv：1711.04043，2017.
[52] 王阳刚，邱锡鹏，黄萱菁，等.基于双通道图神经网络的小样本文本分类[J].中文信息学报，2021，35（7）：89-97.
WANG Y G，QIU X P，HUANG X Q，et al，Few-shot text classification with dual channel graph neural networks[J].Journal of Chinese Information Processing，2021，35（7）：89-97.
[53] XIE Y，XU H，LI J，et al.Heterogeneous graph neural networks for noisy few-shot relation classification[J].Knowledge-Based Systems，2020，194：105548.
[54] GUO X，TIAN B，TIAN X.HFGNN-Proto：hesitant fuzzy graph neural network-based prototypical network for few-shot text classification[J].Electronics，2022，11（15）：2423.
[55] LYU C，LIU W，WANG P.Few-shot text classification with edge-labeling graph neural network-based prototypical network[C]//Proceedings of the 28th International Conference on Computational Linguistics，2020：5547-5552.
[56] WHITE J.PubMed 2.0[J].Medical Reference Services Quarterly，2020，39（4）：382-387.
[57] BODENREIDER O.The unified medical language system（UMLS）：integrating biomedical terminology[J].Nucleic Acids Research，2004，32：267-270.
[58] HAN Y，QIAO L，ZHENG J，et al.Multi-view interaction learning for few-shot relation classification[C]//Procee-dings of the 30th ACM International Conference on Information & Knowledge Management，2021：649-658.
[59] ZHEN L，ZHANG Y，NIE J Y，et al.Improving few-shot relation classification by prototypical represent-ation learning with definition text[C]//Findings of the Association for Computational Linguistics，2022：454-464.
[60] LIU Y，HU J，WAN X，et al.Learn from relation information：towards prototype representation rectification for few-shot relation extraction[C]//Findings of the Association for Computational Linguistics，2022：1822-1831.
[61] GENG X，CHEN X，ZHU K Q，et al.Mick：a meta-learning framework for few-shot relation classification with small training data[C]//Proceedings of the 29th ACM International Conference on Information & Knowledge Management，2020：415-424.
[62] XU S，XIANG Y.Frog-GNN：multi-perspective aggregation based graph neural network for few-shot text classification[J].Expert Systems with Applications，2021，176：114795.
[63] WANG X，HAN X，HUANG W，et al.Multi-similarity loss with general pair weighting for deep metric learning[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2019：5022-5030.
[64] SHRIVASTAVA A，GUPTA A，GIRSHICK R.Training region-based object detectors with online hard example mining[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2016：761-769.
[65] XIE R，LIU Z，LUAN H，et al.Image-embodied knowledge representation learning[J].arXiv：1609.07028，2016.
[66] SCHICK T，SCHüTZE H.It’s not just size that matters：small language models are also few-shot learners[J].arXiv：2009.07118，2020.
[67] LIU X，JI K，FU Y，et al.P-tuning：prompt tuning can be comparable to fine-tuning across scales and tasks[C]//Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics（Volume 2：Short Papers），2022：61-68.
[68] GU Y，HAN X，LIU Z，et al.PPT：pre-trained prompt tuning for few-shot learning[C]//Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics（Volume 1：Long Papers），2022：8410-8423.
[69] WANG X，ZHU M，BO D，et al.Am-GCN：adaptive multi-channel graph convolutional networks[C]//Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining，2020：1243-1253.
[70] BO D，WANG X，SHI C，et al.Beyond low-frequency information in graph convolutional networks[C]//Proc-eedings of the AAAI Conference on Artificial Intelligence，2021：3950-3957.
[71] PEREZ E，KIELA D，CHO K.True few-shot learning with language models[C]//Advances in Neural Information Pro-cessing Systems，2021：11054-11070.