skip to main content
research-article

Transfer Learning for Low-Resource Multilingual Relation Classification

Published:23 March 2023Publication History
Skip Abstract Section

Abstract

Relation classification (sometimes called relation extraction) requires trustworthy datasets for fine-tuning large language models, as well as for evaluation. Data collection is challenging for Indian languages, because they are syntactically and morphologically diverse, as well as different from resource-rich languages like English. Despite recent interest in deep generative models for Indian languages, relation classification is still not well served by public datasets. In response, we present IndoRE, a dataset with 21K entity- and relation-tagged gold sentences in three Indian languages (Bengali, Hindi, and Telugu), plus English. We start with a multilingual BERT (mBERT)-based system that captures entity span positions and type information, and provides competitive performance on monolingual relation classification. Using this baseline system, we explore transfer mechanisms between languages and the scope to reduce expensive data annotation while achieving reasonable relation extraction performance. Specifically, we

(a)

study the accuracy-efficiency trade-off between expensive, manually labeled gold instances vs. automatically translated and aligned silver instances to train a relation extractor,

(b)

device a simple mechanism for budgeted gold data annotation by intelligently converting distant-supervised silver training instances to gold training instances with human annotators using active learning, and finally

(c)

propose an ensemble model to provide a performance boost over that achieved via limited gold training instances.

We release the dataset for future research.1

REFERENCES

  1. [1] Angluin Dana. 1988. Queries and concept learning. Machine Learning 2, 4 (1988), 319342.Google ScholarGoogle ScholarCross RefCross Ref
  2. [2] Ash Jordan T., Zhang Chicheng, Krishnamurthy Akshay, Langford John, and Agarwal Alekh. 2019. Deep batch active learning by diverse, uncertain gradient lower bounds. arXiv preprint arXiv:1906.03671.Google ScholarGoogle Scholar
  3. [3] Balcan Maria-Florina, Beygelzimer Alina, and Langford John. 2009. Agnostic active learning. Journal of Computer and System Sciences 75, 1 (2009), 7889.Google ScholarGoogle ScholarDigital LibraryDigital Library
  4. [4] Soares Livio Baldini, FitzGerald Nicholas, Ling Jeffrey, and Kwiatkowski Tom. 2019. Matching the blanks: Distributional similarity for relation learning. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 28952905. Google ScholarGoogle ScholarCross RefCross Ref
  5. [5] Bastos Anson, Nadgeri Abhishek, Singh Kuldeep, Mulang Isaiah Onando, Shekarpour Saeedeh, Hoffart Johannes, and Kaul Manohar. 2020. RECON: Relation extraction using knowledge graph context in a graph neural network. In Proceedings of the Web Conference 2021 (WWW’21). Google ScholarGoogle ScholarCross RefCross Ref
  6. [6] Bekoulis Giannis, Deleu Johannes, Demeester Thomas, and Develder Chris. 2018. Adversarial training for multi-context joint entity and relation extraction. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. 28302836. Google ScholarGoogle ScholarCross RefCross Ref
  7. [7] Beluch William H., Genewein Tim, Nürnberger Andreas, and Köhler Jan M.. 2018. The power of ensembles for active learning in image classification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 93689377.Google ScholarGoogle ScholarCross RefCross Ref
  8. [8] Beygelzimer Alina, Dasgupta Sanjoy, and Langford John. 2009. Importance weighted active learning. In Proceedings of the 26th Annual International Conference on Machine Learning. 4956.Google ScholarGoogle ScholarDigital LibraryDigital Library
  9. [9] Bilgic Mustafa and Getoor Lise. 2009. Link-based active learning. In Proceedings of the NIPS Workshop on Analyzing Networks and Learning with Graphs, Vol. 4.Google ScholarGoogle Scholar
  10. [10] Bloodgood Michael and Callison-Burch Chris. 2014. Bucking the trend: Large-scale cost-focused active learning for statistical machine translation. arXiv preprint arXiv:1410.5877.Google ScholarGoogle Scholar
  11. [11] Blundell Charles, Cornebise Julien, Kavukcuoglu Koray, and Wierstra Daan. 2015. Weight uncertainty in neural network. In Proceedings of the International Conference on Machine Learning. 16131622.Google ScholarGoogle Scholar
  12. [12] Cai Rui, Zhang Xiaodong, and Wang Houfeng. 2016. Bidirectional recurrent convolutional neural network for relation classification. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 756765. Google ScholarGoogle ScholarCross RefCross Ref
  13. [13] Chen Jun, Hoehndorf Robert, Elhoseiny Mohamed, and Zhang Xiangliang. 2020. Efficient long-distance relation extraction with DG-SpanBERT. arXiv preprint arXiv:2004.03636. Google ScholarGoogle ScholarCross RefCross Ref
  14. [14] Chen Miao, Lan Ganhui, Du Fang, and Lobanov Victor. 2020. Joint learning with pre-trained transformer on named entity recognition and relation extraction tasks for clinical analytics. In Proceedings of the 3rd Clinical Natural Language Processing Workshop. 234242. Google ScholarGoogle ScholarCross RefCross Ref
  15. [15] Dagan Ido and Engelson Sean P.. 1995. Committee-based sampling for training probabilistic classifiers. In Proceedings of the 12th International Conference on Machine Learning. 150157.Google ScholarGoogle ScholarDigital LibraryDigital Library
  16. [16] Dasgupta Sanjoy, Kalai Adam Tauman, and Monteleoni Claire. 2005. Analysis of perceptron-based active learning. In Proceedings of the International Conference on Computational Learning Theory. 249263.Google ScholarGoogle ScholarDigital LibraryDigital Library
  17. [17] Santos Cícero dos, Xiang Bing, and Zhou Bowen. 2015. Classifying relations by ranking with convolutional neural 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). 626634. Google ScholarGoogle ScholarCross RefCross Ref
  18. [18] Eberts Markus and Ulges Adrian. 2019. Span-based joint entity and relation extraction with transformer pre-training. arxiv:cs.CL/1909.07755.Google ScholarGoogle Scholar
  19. [19] Figueroa Rosa L., Zeng-Treitler Qing, Ngo Long H., Goryachev Sergey, and Wiechmann Eduardo P.. 2012. Active learning for clinical text classification: Is it better than random sampling? Journal of the American Medical Informatics Association 19, 5 (2012), 809816.Google ScholarGoogle ScholarCross RefCross Ref
  20. [20] Freund Yoav, Seung H. Sebastian, Shamir Eli, and Tishby Naftali. 1997. Selective sampling using the query by committee algorithm. Machine Learning 28, 2 (1997), 133168.Google ScholarGoogle ScholarDigital LibraryDigital Library
  21. [21] Freytag Alexander, Rodner Erik, and Denzler Joachim. 2014. Selecting influential examples: Active learning with expected model output changes. In Proceedings of the European Conference on Computer Vision. 562577.Google ScholarGoogle ScholarCross RefCross Ref
  22. [22] Fu Tsu-Jui, Li Peng-Hsuan, and Ma Wei-Yun. 2019. GraphRel: Modeling text as relational graphs for joint entity and relation extraction. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 14091418. Google ScholarGoogle ScholarCross RefCross Ref
  23. [23] Gal Yarin and Ghahramani Zoubin. 2016. Dropout as a Bayesian approximation: Representing model uncertainty in deep learning. In Proceedings of the International Conference on Machine Learning. 10501059.Google ScholarGoogle ScholarDigital LibraryDigital Library
  24. [24] Gal Yarin, Islam Riashat, and Ghahramani Zoubin. 2017. Deep Bayesian active learning with image data. In Proceedings of the International Conference on Machine Learning. 11831192.Google ScholarGoogle Scholar
  25. [25] Goodfellow Ian J., Mirza Mehdi, Xiao Da, Courville Aaron, and Bengio Yoshua. 2013. An empirical investigation of catastrophic forgetting in gradient-based neural networks. arXiv preprint arXiv:1312.6211.Google ScholarGoogle Scholar
  26. [26] Guo Yuhong. 2010. Active instance sampling via matrix partition. In Advances in Neural Information Processing Systems (NIPS’10). 802810.Google ScholarGoogle Scholar
  27. [27] Haffari Gholamreza, Roy Maxim, and Sarkar Anoop. 2009. Active learning for statistical phrase-based machine translation. In Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics. 415423.Google ScholarGoogle ScholarDigital LibraryDigital Library
  28. [28] Han Xu, Yu Pengfei, Liu Zhiyuan, Sun Maosong, and Li Peng. 2018. Hierarchical relation extraction with coarse-to-fine grained attention. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. 22362245. Google ScholarGoogle ScholarCross RefCross Ref
  29. [29] Han Xu, Zhu Hao, Yu Pengfei, Wang Ziyun, Yao Yuan, Liu Zhiyuan, and Sun Maosong. 2018. FewRel: A large-scale supervised few-shot relation classification dataset with state-of-the-art evaluation. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. 48034809. Google ScholarGoogle ScholarCross RefCross Ref
  30. [30] Hendrickx Iris, Kim Su Nam, Kozareva Zornitsa, Nakov Preslav, Séaghdha Diarmuid Ó., Padó Sebastian, Pennacchiotti Marco, Romano Lorenza, and Szpakowicz Stan. 2010. SemEval-2010 task 8: Multi-way classification of semantic relations between pairs of nominals. In Proceedings of the 5th International Workshop on Semantic Evaluation. 3338. https://www.aclweb.org/anthology/S10-1006.Google ScholarGoogle ScholarDigital LibraryDigital Library
  31. [31] Hoffmann Raphael, Zhang Congle, Ling Xiao, Zettlemoyer Luke, and Weld Daniel S.. 2011. Knowledge-based weak supervision for information extraction of overlapping relations. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies. 541550. https://www.aclweb.org/anthology/P11-1055.Google ScholarGoogle ScholarDigital LibraryDigital Library
  32. [32] Jiang Xiaotian, Wang Quan, Li Peng, and Wang Bin. 2016. Relation extraction with multi-instance multi-label convolutional neural networks. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers. 14711480. https://www.aclweb.org/anthology/C16-1139.Google ScholarGoogle Scholar
  33. [33] Jin Zhijing, Yang Yongyi, Qiu Xipeng, and Zhang Zheng. 2020. Relation of the relations: A new paradigm of the relation extraction problem. arXiv preprint arXiv:2006.03719. Google ScholarGoogle ScholarCross RefCross Ref
  34. [34] Joshi Ajay J., Porikli Fatih, and Papanikolopoulos Nikolaos. 2009. Multi-class active learning for image classification. In Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, Los Alamitos, CA, 23722379.Google ScholarGoogle ScholarCross RefCross Ref
  35. [35] Joshi Mandar, Chen Danqi, Liu Yinhan, Weld Daniel S., Zettlemoyer Luke, and Levy Omer. 2020. SpanBERT: Improving pre-training by representing and predicting spans. Transactions of the Association for Computational Linguistics 8 (2020), 6477. Google ScholarGoogle ScholarCross RefCross Ref
  36. [36] Kemker Ronald, McClure Marc, Abitino Angelina, Hayes Tyler, and Kanan Christopher. 2018. Measuring catastrophic forgetting in neural networks. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 32.Google ScholarGoogle ScholarCross RefCross Ref
  37. [37] Khanuja Simran, Johnson Melvin, and Talukdar Partha. 2021. MergeDistill: Merging pre-trained language models using distillation. arxiv:cs.CL/2106.02834.Google ScholarGoogle Scholar
  38. [38] King Ross D., Whelan Kenneth E., Jones Ffion M., Reiser Philip G. K., Bryant Christopher H., Muggleton Stephen H., Kell Douglas B., and Oliver Stephen G.. 2004. Functional genomic hypothesis generation and experimentation by a robot scientist. Nature 427, 6971 (2004), 247252.Google ScholarGoogle ScholarCross RefCross Ref
  39. [39] Kirkpatrick James, Pascanu Razvan, Rabinowitz Neil, Veness Joel, Desjardins Guillaume, Rusu Andrei A., Milan Kieran, et al. 2017. Overcoming catastrophic forgetting in neural networks. Proceedings of the National Academy of Sciences 114, 13 (2017), 35213526.Google ScholarGoogle ScholarCross RefCross Ref
  40. [40] Kozhevnikov Mikhail and Titov Ivan. 2014. Cross-lingual model transfer using feature representation projection. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). 579585. Google ScholarGoogle ScholarCross RefCross Ref
  41. [41] Krishnamurthy Vikram. 2002. Algorithms for optimal scheduling and management of hidden Markov model sensors. IEEE Transactions on Signal Processing 50, 6 (2002), 13821397.Google ScholarGoogle ScholarDigital LibraryDigital Library
  42. [42] Lee Joohong, Seo Sangwoo, and Choi Yong Suk. 2019. Semantic relation classification via bidirectional LSTM networks with entity-aware attention using latent entity typing. arXiv preprint arXiv:1901.08163. Google ScholarGoogle ScholarCross RefCross Ref
  43. [43] Lee Ji Young, Dernoncourt Franck, and Szolovits Peter. 2017. MIT at SemEval-2017 task 10: Relation extraction with convolutional neural networks. In Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval’17). 978984. Google ScholarGoogle ScholarCross RefCross Ref
  44. [44] Lewis David D. and Gale William A.. 1995. A sequential algorithm for training text classifiers. ACM SIGIR Forum 29, 2 (1995), 13–19.Google ScholarGoogle Scholar
  45. [45] Lin Yankai, Shen Shiqi, Liu Zhiyuan, Luan Huanbo, and Sun Maosong. 2016. Neural relation extraction with selective attention over instances. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 21242133. Google ScholarGoogle ScholarCross RefCross Ref
  46. [46] Liu Tianyi, Zhang Xinsong, Zhou Wanhao, and Jia Weijia. 2018. Neural relation extraction via inner-sentence noise reduction and transfer learning. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. 21952204. Google ScholarGoogle ScholarCross RefCross Ref
  47. [47] Liu Yang, Wei Furu, Li Sujian, Ji Heng, Zhou Ming, and Wang Houfeng. 2015. A dependency-based neural network for relation classification. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers). 285290. Google ScholarGoogle ScholarCross RefCross Ref
  48. [48] McCallumzy Andrew Kachites and Nigamy Kamal. 1998. Employing EM and pool-based active learning for text classification. In Proceedings of the International Conference on Machine Learning (ICML’98). 359367.Google ScholarGoogle Scholar
  49. [49] Mintz Mike, Bills Steven, Snow Rion, and Jurafsky Daniel. 2009. Distant supervision for relation extraction without labeled data. In 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. 10031011. https://www.aclweb.org/anthology/P09-1113.Google ScholarGoogle ScholarDigital LibraryDigital Library
  50. [50] Miwa Makoto and Bansal Mohit. 2016. End-to-end relation extraction using LSTMs on sequences and tree structures. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 11051116. Google ScholarGoogle ScholarCross RefCross Ref
  51. [51] Nadgeri Abhishek, Bastos Anson, Singh Kuldeep, Mulang Isaiah Onando, Hoffart Johannes, Shekarpour Saeedeh, and Saraswat Vijay. 2021. KGPool: Dynamic knowledge graph context selection for relation extraction. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021. Association for Computational Linguistics, 535548. Google ScholarGoogle ScholarCross RefCross Ref
  52. [52] Nag Arijit, Samanta Bidisha, Mukherjee Animesh, Ganguly Niloy, and Chakrabarti Soumen. 2021. A data bootstrapping recipe for low-resource multilingual relation classification. In Proceedings of the 25th Conference on Computational Natural Language Learning. 575587.Google ScholarGoogle ScholarCross RefCross Ref
  53. [53] Nguyen Dat Quoc and Verspoor Karin. 2019. End-to-end neural relation extraction using deep biaffine attention. Advances in Information Retrieval 2019 (2019), 729738. Google ScholarGoogle ScholarCross RefCross Ref
  54. [54] Nguyen Hieu T. and Smeulders Arnold. 2004. Active learning using pre-clustering. In Proceedings of the 21st International Conference on Machine Learning. 79.Google ScholarGoogle ScholarDigital LibraryDigital Library
  55. [55] Nguyen Thien Huu and Grishman Ralph. 2015. Relation extraction: Perspective from convolutional neural networks. In Proceedings of the 1st Workshop on Vector Space Modeling for Natural Language Processing. 3948. Google ScholarGoogle ScholarCross RefCross Ref
  56. [56] Ni Jian, Moon Taesun, Awasthy Parul, and Florian Radu. 2020. Cross-lingual relation extraction with transformers. arxiv:cs.CL/2010.08652.Google ScholarGoogle Scholar
  57. [57] Pfeiffer Jonas, Rücklé Andreas, Poth Clifton, Kamath Aishwarya, Vulić Ivan, Ruder Sebastian, Cho Kyunghyun, and Gurevych Iryna. 2020. AdapterHub: A framework for adapting transformers. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Systems Demonstrations (EMNLP’20). 4654. https://www.aclweb.org/anthology/2020.emnlp-demos.7.Google ScholarGoogle ScholarCross RefCross Ref
  58. [58] Pfeiffer Jonas, Vulić Ivan, Gurevych Iryna, and Ruder Sebastian. 2020. MAD-X: An adapter-based framework for multi-task cross-lingual transfer. arxiv:cs.CL/2005.00052.Google ScholarGoogle Scholar
  59. [59] Pires Telmo, Schlinger Eva, and Garrette Dan. 2019. How multilingual is multilingual BERT?arxiv:cs.CL/1906.01502.Google ScholarGoogle Scholar
  60. [60] Ranganathan Hiranmayi, Venkateswara Hemanth, Chakraborty Shayok, and Panchanathan Sethuraman. 2017. Deep active learning for image classification. In Proceedings of the 2017 IEEE International Conference on Image Processing (ICIP’17). IEEE, Los Alamitos, CA, 39343938.Google ScholarGoogle ScholarDigital LibraryDigital Library
  61. [61] Riedel Sebastian, Yao Limin, and McCallum Andrew. 2010. Modeling relations and their mentions without labeled text. In Machine Learning and Knowledge Discovery in Databases, Lecture Notes in Computer Science, Vol. 10535. Springer, 148–163. Google ScholarGoogle Scholar
  62. [62] Roy Nicholas and McCallum Andrew. 2001. Toward optimal active learning through Monte Carlo estimation of error reduction. ICML, Williamstown 2 (2001), 441448.Google ScholarGoogle Scholar
  63. [63] Serra Joan, Suris Didac, Miron Marius, and Karatzoglou Alexandros. 2018. Overcoming catastrophic forgetting with hard attention to the task. In Proceedings of the International Conference on Machine Learning. 45484557.Google ScholarGoogle Scholar
  64. [64] Settles Burr, Craven Mark, and Ray Soumya. 2007. Multiple-instance active learning. Advances in Neural Information Processing Systems 20 (2007), 12891296.Google ScholarGoogle Scholar
  65. [65] Seung H. Sebastian, Opper Manfred, and Sompolinsky Haim. 1992. Query by committee. In Proceedings of the 5th Annual Workshop on Computational Learning Theory. 287294.Google ScholarGoogle ScholarDigital LibraryDigital Library
  66. [66] Sha Fei and Saul Lawrence K.. 2007. Large margin hidden Markov models for automatic speech recognition. Advances in Neural Information Processing Systems 19 (2007), 1249.Google ScholarGoogle Scholar
  67. [67] Shen Yatian and Huang Xuanjing. 2016. Attention-based convolutional neural network for semantic relation extraction. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers. 25262536. https://www.aclweb.org/anthology/C16-1238.Google ScholarGoogle Scholar
  68. [68] Shen Yanyao, Yun Hyokun, Lipton Zachary C., Kronrod Yakov, and Anandkumar Animashree. 2017. Deep active learning for named entity recognition. arXiv preprint arXiv:1707.05928.Google ScholarGoogle Scholar
  69. [69] Shui Changjian, Zhou Fan, Gagné Christian, and Wang Boyu. 2020. Deep active learning: Unified and principled method for query and training. In Proceedings of the International Conference on Artificial Intelligence and Statistics. 13081318.Google ScholarGoogle Scholar
  70. [70] Soares Livio Baldini, FitzGerald Nicholas, Ling Jeffrey, and Kwiatkowski Tom. 2019. Matching the blanks: Distributional similarity for relation learning. arxiv:cs.CL/1906.03158.Google ScholarGoogle Scholar
  71. [71] Surdeanu Mihai, Tibshirani Julie, Nallapati Ramesh, and Manning Christopher D.. 2012. Multi-instance multi-label learning for relation extraction. In Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning. 455465. https://www.aclweb.org/anthology/D12-1042.Google ScholarGoogle ScholarDigital LibraryDigital Library
  72. [72] Thompson Cynthia A., Califf Mary Elaine, and Mooney Raymond J.. 1999. Active learning for natural language parsing and information extraction. In Proceedings of the 16th International Conference on Machine Learning (ICML’99). 406414.Google ScholarGoogle Scholar
  73. [73] Tong Simon and Koller Daphne. 2001. Support vector machine active learning with applications to text classification. Journal of Machine Learning Research 2 (Nov. 2001), 4566.Google ScholarGoogle Scholar
  74. [74] Vashishth Shikhar, Joshi Rishabh, Prayaga Sai Suman, Bhattacharyya Chiranjib, and Talukdar Partha. 2018. RESIDE: Improving distantly-supervised neural relation extraction using side information. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. 12571266. Google ScholarGoogle ScholarCross RefCross Ref
  75. [75] Wang Jue and Lu Wei. 2020. Two are better than one: Joint entity and relation extraction with table-sequence encoders. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP’20). 17061721. Google ScholarGoogle ScholarCross RefCross Ref
  76. [76] Wang Linlin, Cao Zhu, Melo Gerard de, and Liu Zhiyuan. 2016. Relation classification via multi-level attention CNNs. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 12981307. Google ScholarGoogle ScholarCross RefCross Ref
  77. [77] Wang Xinyi, Tsvetkov Yulia, Ruder Sebastian, and Neubig Graham. 2021. Efficient test time adapter ensembling for low-resource language varieties. In Findings of the Association for Computational Linguistics: EMNLP 2021. Association for Computational Linguistics, 730737. Google ScholarGoogle ScholarCross RefCross Ref
  78. [78] Wu Shanchan and He Yifan. 2019. Enriching pre-trained language model with entity information for relation classification. arXiv preprint arXiv:1905.08284. Google ScholarGoogle ScholarCross RefCross Ref
  79. [79] Wu Yi, Bamman David, and Russell Stuart. 2017. Adversarial training for relation extraction. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. 17781783. Google ScholarGoogle ScholarCross RefCross Ref
  80. [80] Xiao Minguang and Liu Cong. 2016. Semantic relation classification via hierarchical recurrent neural network with attention. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers. 12541263. https://www.aclweb.org/anthology/C16-1119.Google ScholarGoogle Scholar
  81. [81] Xu Kun, Feng Yansong, Huang Songfang, and Zhao Dongyan. 2015. Semantic relation classification via convolutional neural networks with simple negative sampling. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. 536540. Google ScholarGoogle ScholarCross RefCross Ref
  82. [82] Xu Yan, Jia Ran, Mou Lili, Li Ge, Chen Yunchuan, Lu Yangyang, and Jin Zhi. 2016. Improved relation classification by deep recurrent neural networks with data augmentation. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers. 14611470. https://www.aclweb.org/anthology/C16-1138.Google ScholarGoogle Scholar
  83. [83] Xu Yan, Mou Lili, Li Ge, Chen Yunchuan, Peng Hao, and Jin Zhi. 2015. Classifying relations via long short term memory networks along shortest dependency paths. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. 17851794. Google ScholarGoogle ScholarCross RefCross Ref
  84. [84] Xue Fuzhao, Sun Aixin, Zhang Hao, and Chng Eng Siong. 2020. GDPNet: Refining latent multi-view graph for relation extraction. arXiv preprint arXiv:2012.06780. Google ScholarGoogle ScholarCross RefCross Ref
  85. [85] Yamada Ikuya, Asai Akari, Shindo Hiroyuki, Takeda Hideaki, and Matsumoto Yuji. 2020. LUKE: Deep contextualized entity representations with entity-aware self-attention. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP’20). 64426454. Google ScholarGoogle ScholarCross RefCross Ref
  86. [86] Ye Zhi-Xiu and Ling Zhen-Hua. 2019. Distant supervision relation extraction with intra-bag and inter-bag attentions. In 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). 28102819. Google ScholarGoogle ScholarCross RefCross Ref
  87. [87] Yin Changchang, Qian Buyue, Cao Shilei, Li Xiaoyu, Wei Jishang, Zheng Qinghua, and Davidson Ian. 2017. Deep similarity-based batch mode active learning with exploration-exploitation. In Proceedings of the 2017 IEEE International Conference on Data Mining (ICDM’17). IEEE, Los Alamitos, CA, 575584.Google ScholarGoogle ScholarCross RefCross Ref
  88. [88] Zeng Daojian, Liu Kang, Chen Yubo, and Zhao Jun. 2015. Distant supervision for relation extraction via piecewise convolutional neural networks. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. 17531762. Google ScholarGoogle ScholarCross RefCross Ref
  89. [89] Zeng Daojian, Liu Kang, Lai Siwei, Zhou Guangyou, and Zhao Jun. 2014. Relation classification via convolutional deep neural network. In Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers. 23352344. https://www.aclweb.org/anthology/C14-1220.Google ScholarGoogle Scholar
  90. [90] Zeng Wenyuan, Lin Yankai, Liu Zhiyuan, and Sun Maosong. 2017. Incorporating relation paths in neural relation extraction. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. 17681777. Google ScholarGoogle ScholarCross RefCross Ref
  91. [91] Zhang Chicheng. 2018. Efficient active learning of sparse halfspaces. In Proceedings of the Conference on Learning Theory. 18561880.Google ScholarGoogle Scholar
  92. [92] Zhang Dongxu and Wang Dong. 2015. Relation classification via recurrent neural network. arXiv preprint arXiv:1508.01006. Google ScholarGoogle ScholarCross RefCross Ref
  93. [93] Zhang Shu, Zheng Dequan, Hu Xinchen, and Yang Ming. 2015. Bidirectional long short-term memory networks for relation classification. In Proceedings of the 29th Pacific Asia Conference on Language, Information, and Computation. 7378. https://www.aclweb.org/anthology/Y15-1009.Google ScholarGoogle Scholar
  94. [94] Zhang Yuhao, Zhong Victor, Chen Danqi, Angeli Gabor, and Manning Christopher D.. 2017. Position-aware attention and supervised data improve slot filling. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. 3545. Google ScholarGoogle ScholarCross RefCross Ref
  95. [95] Zhdanov Fedor. 2019. Diverse mini-batch active learning. arXiv preprint arXiv:1901.05954.Google ScholarGoogle Scholar
  96. [96] Zheng Suncong, Wang Feng, Bao Hongyun, Hao Yuexing, Zhou Peng, and Xu Bo. 2017. Joint extraction of entities and relations based on a novel tagging scheme. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 12271236. Google ScholarGoogle ScholarCross RefCross Ref
  97. [97] Zhou Peng, Shi Wei, Tian Jun, Qi Zhenyu, Li Bingchen, Hao Hongwei, and Xu Bo. 2016. Attention-based bidirectional long short-term memory networks for relation classification. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). 207212. Google ScholarGoogle ScholarCross RefCross Ref

Index Terms

  1. Transfer Learning for Low-Resource Multilingual Relation Classification

      Recommendations

      Comments

      Login options

      Check if you have access through your login credentials or your institution to get full access on this article.

      Sign in

      Full Access

      • Published in

        cover image ACM Transactions on Asian and Low-Resource Language Information Processing
        ACM Transactions on Asian and Low-Resource Language Information Processing  Volume 22, Issue 2
        February 2023
        624 pages
        ISSN:2375-4699
        EISSN:2375-4702
        DOI:10.1145/3572719
        Issue’s Table of Contents

        Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

        Publisher

        Association for Computing Machinery

        New York, NY, United States

        Publication History

        • Published: 23 March 2023
        • Online AM: 8 August 2022
        • Accepted: 21 July 2022
        • Revised: 29 June 2022
        • Received: 22 March 2022
        Published in tallip Volume 22, Issue 2

        Permissions

        Request permissions about this article.

        Request Permissions

        Check for updates

        Qualifiers

        • research-article
      • Article Metrics

        • Downloads (Last 12 months)215
        • Downloads (Last 6 weeks)22

        Other Metrics

      PDF Format

      View or Download as a PDF file.

      PDF

      eReader

      View online with eReader.

      eReader

      Full Text

      View this article in Full Text.

      View Full Text

      HTML Format

      View this article in HTML Format .

      View HTML Format
      About Cookies On This Site

      We use cookies to ensure that we give you the best experience on our website.

      Learn more

      Got it!