Abstract
Lack of annotated data is a major concern in Event Detection (ED) tasks for low-resource languages. Cross-lingual ED seeks to address this issue by transferring information across various languages to improve overall performance. In this article, we propose a method for cross-lingual ED with a few training instances. We present a model agnostic meta-learning approach for few-shot cross-lingual ED that is able to find good parameter initialization and enables fast adaptation to new low-resource languages. We evaluate our model on four Indian languages. The results show that our approach significantly outperforms the base model.
- [1] Zishan Ahmad, Sovan Kumar Sahoo, Asif Ekbal, and Pushpak Bhattacharyya. 2018. A deep learning model for event extraction and classification in Hindi for disaster domain. 15th International Conference on Natural Language Processing, 127.Google Scholar
- [2] . 2006. The stages of event extraction. In Proceedings of the Workshop on Annotating and Reasoning about Time and Events (Sydney, Australia) (
ARTE’06 ). Association for Computational Linguistics, USA, 1–8. Google ScholarDigital Library
- [3] . 2021. XOR QA: Cross-lingual open-retrieval question answering. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, Online, 547–564.
DOI: Google ScholarCross Ref
- [4] . 2021. Nearest neighbour few-shot learning for cross-lingual classification. arXiv preprint arXiv:2109.02221 (2021).Google Scholar
- [5] Jiaxin Chen, Li-Ming Zhan, Xiao-Ming Wu, and Fu-lai Chung. 2020. Variational metric scaling for metric-based meta-learning. In Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 34, AAAI Press, New York, NY, 3478–3485.Google Scholar
- [6] . 2015. Event extraction via dynamic multi-pooling 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). Association for Computational Linguistics, Beijing, China, 167–176.
DOI: Google ScholarCross Ref
- [7] . 2009. Can one language bootstrap the other: A case study on event extraction. In Proceedings of the NAACL HLT 2009 Workshop on Semi-Supervised Learning for Natural Language Processing (Boulder, Colorado) (SemiSupLearn’09). Association for Computational Linguistics, USA, 66–74. Google Scholar
Cross Ref
- [8] . 2019. Cross-lingual natural language generation via pre-training. arXiv:1909.10481 [cs.CL]Google Scholar
- [9] . 2021. Few-shot event detection with prototypical amortized conditional random field. arXiv:2012.02353 [cs.CL]Google Scholar
- [10] . 2019. Unsupervised cross-lingual representation learning at scale. arXiv preprint arXiv:1911.02116.Google Scholar
- [11] . 2020. Edge-enhanced graph convolution networks for event detection with syntactic relation. arXiv:2002.10757 [cs.CL]Google Scholar
- [12] . 2020. Meta-learning with dynamic-memory-based prototypical network for few-shot event detection. Proceedings of the 13th International Conference on Web Search and Data Mining (
Jan 2020).DOI: Google ScholarDigital Library
- [13] . 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. arXiv:1810.04805 [cs.CL]Google Scholar
- [14] . 2019. Investigating meta-learning algorithms for low-resource natural language understanding tasks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). Association for Computational Linguistics, Hong Kong, China, 1192–1197.
DOI: Google ScholarCross Ref
- [15] . 2018. The hitchhiker’s guide to testing statistical significance in natural language processing. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 1383–1392.Google Scholar
Cross Ref
- [16] . 2020. Multi-sentence argument linking. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Online, 8057–8077.
DOI: Google ScholarCross Ref
- [17] . 2017. Model-agnostic meta-learning for fast adaptation of deep networks. In International Conference on Machine Learning. PMLR, 1126–1135.Google Scholar
Digital Library
- [18] . 1999. Catastrophic forgetting in connectionist networks. Trends in Cognitive Sciences 3 (
5 1999), 128–135.DOI: Google ScholarCross Ref
- [19] . 2019. Few-shot classification in named entity recognition task. In Proceedings of the 34th ACM/SIGAPP Symposium on Applied Computing. 993–1000.Google Scholar
Digital Library
- [20] . 2017. Few-shot learning with graph neural networks. arXiv preprint arXiv:1711.04043 (2017).Google Scholar
- [21] . 2018. Meta-learning for low-resource neural machine translation. arXiv:1808.08437 [cs.CL]Google Scholar
- [22] . 2011. Using cross-entity inference to improve event extraction. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, Portland, OR, 1127–1136. https://aclanthology.org/P11-1113.Google Scholar
Digital Library
- [23] . 2020. Few-shot slot tagging with collapsed dependency transfer and label-enhanced task-adaptive projection network. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Online, 1381–1393.
DOI: Google ScholarCross Ref
- [24] . 2016. Leveraging multilingual training for limited resource event extraction. In Proceedings of the 26th International Conference on Computational Linguistics (COLING’16): Technical Papers. The COLING 2016 Organizing Committee, Osaka, Japan, 1201–1210. https://aclanthology.org/C16-1114.Google Scholar
- [25] . 2008. Refining event extraction through cross-document inference. In Proceedings of ACL-08: HLT. Association for Computational Linguistics, Columbus, OH, 254–262. https://aclanthology.org/P08-1030.Google Scholar
- [26] . 2020. iNLPSuite: Monolingual corpora, evaluation benchmarks and pre-trained multilingual language models for Indian languages. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Findings. 4948–4961.Google Scholar
- [27] . 2019. Effective cross-lingual transfer of neural machine translation models without shared vocabularies. arXiv preprint arXiv:1905.05475Google Scholar
- [28] . 2015. Adam: A method for stochastic optimization. In ICLR.Google Scholar
- [29] . 2019. Cross-lingual training for automatic question generation. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Florence, Italy, 4863–4872.
DOI: Google ScholarCross Ref
- [30] Viet Dac Lai, Franck Dernoncourt, and Thien Huu Nguyen. 2020. Exploiting the matching information in the support set for few shot event classification. Advances in Knowledge Discovery and Data Mining: 24th Pacific-Asia Conference, Springer-Verlag, Berlin, Heidelberg, 233–245. Google Scholar
Digital Library
- [31] . 2019. ALBERT: A lite BERT for self-supervised learning of language representations. arXiv preprint arXiv:1909.11942Google Scholar
- [32] . 2020. From zero to hero: On the limitations of zero-shot cross-lingual transfer with multilingual transformers. arXiv preprint arXiv:2005.00633Google Scholar
- [33] . 2015. Dbpedia–a large-scale, multilingual knowledge base extracted from Wikipedia. Semantic Web 6, 2 (2015), 167–195.Google Scholar
- [34] . 2013. Joint event extraction via structured prediction with global features. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, Sofia, Bulgaria, 73–82. https://aclanthology.org/P13-1008.Google Scholar
- [35] . 2010. Using document level cross-event inference to improve event extraction. In Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Uppsala, Sweden, 789–797. https://aclanthology.org/P10-1081.Google Scholar
Digital Library
- [36] . 2019. Neural cross-lingual event detection with minimal parallel resources. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). Association for Computational Linguistics, Hong Kong, China, 738–748.
DOI: Google ScholarCross Ref
- [37] . 2018. Exploiting contextual information via dynamic memory network for event detection. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Brussels, Belgium, 1030–1035.
DOI: Google ScholarCross Ref
- [38] . 2021. MLBiNet: A cross-sentence collective event detection network. arXiv:2105.09458 [cs.CL]Google Scholar
- [39] . 2021. Text2Event: Controllable sequence-to-structure generation for end-to-end event extraction. arXiv:2106.09232 [cs.CL]Google Scholar
- [40] . 2019. Tale of tails using rule augmented sequence labeling for event extraction.
DOI: Google ScholarCross Ref
- [41] . 2020. Introducing a new dataset for event detection in cybersecurity texts. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP’20). Association for Computational Linguistics, Online, 5381–5390.
DOI: Google ScholarCross Ref
- [42] . 2019. Penalty method for inversion-free deep bilevel optimization. arXiv preprint arXiv:1911.03432Google Scholar
- [43] . 2017. Meta networks. In International Conference on Machine Learning. PMLR, 2554–2563.Google Scholar
Digital Library
- [44] . 2012. BabelNet: The automatic construction, evaluation and application of a wide-coverage multilingual semantic network. Artificial Intelligence 193 (2012), 217–250.Google Scholar
Digital Library
- [45] . 2016. Joint event extraction via recurrent neural networks. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, San Diego, CA, 300–309.
DOI: Google ScholarCross Ref
- [46] . 2015. Event detection and domain adaptation 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 2: Short Papers). Association for Computational Linguistics, Beijing, China, 365–371.
DOI: Google ScholarCross Ref
- [47] . 2018. On first-order meta-learning algorithms. arXiv preprint arXiv:1803.02999Google Scholar
- [48] . 2020. Zero-shot cross-lingual transfer with meta learning. arXiv:2003.02739 [cs.CL]Google Scholar
- [49] . 2018. Event detection with neural networks: A rigorous empirical evaluation. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Brussels, Belgium, 999–1004.
DOI: Google ScholarCross Ref
- [50] . 2021. Unsupervised Neural Machine Translation for Low-Resource Domains via Meta-Learning. arXiv:2010.09046 [cs.CL]Google Scholar
- [51] . 2021. Unleash GPT-2 power for event detection. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). Association for Computational Linguistics, Online, 6271–6282.
DOI: Google ScholarCross Ref
- [52] . 2019. Domain adaptive dialog generation via meta learning. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Florence, Italy, 2639–2649.
DOI: Google ScholarCross Ref
- [53] . 2022. Advancing Chinese event detection via revisiting character information. ACM Transactions on Asian and Low-Resource Language Information Processing 21, 4, Article
78 (Feb 2022), 9 pages.DOI: Google ScholarDigital Library
- [54] . 2017. Optimization as a model for few-shot learning. International Conference on Learning Representations. https://openreview.net/forum?id=rJY0-Kcl.Google Scholar
- [55] . 2019. A multi-task model for multilingual trigger detection and classification. In Proceedings of the 16th International Conference on Natural Language Processing. NLP Association of India, International Institute of Information Technology, Hyderabad, India, 160–169. https://aclanthology.org/2019.icon-1.19.Google Scholar
- [56] . 2020. A platform for event extraction in Hindi. In Proceedings of the 12th Language Resources and Evaluation Conference. European Language Resources Association, Marseille, France, 2241–2250. https://aclanthology.org/2020.lrec-1.273.Google Scholar
- [57] . 2016. Meta-learning with memory-augmented neural networks. In International Conference on Machine Learning. PMLR, 1842–1850.Google Scholar
Digital Library
- [58] . 2021. CasEE: A joint learning framework with cascade decoding for overlapping event extraction. arXiv:2107.01583 [cs.CL]Google Scholar
- [59] . 2017. Prototypical networks for few-shot learning. arXiv preprint arXiv:1703.05175Google Scholar
- [60] . 2020. Image enhanced event detection in news articles. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34. 9040–9047.Google Scholar
Cross Ref
- [61] . 2020. Improving event detection via open-domain trigger knowledge. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Online, 5887–5897.
DOI: Google ScholarCross Ref
- [62] . 2017. Attention is all you need. arXiv:1706.03762 [cs.CL]Google Scholar
- [63] Oriol Vinyals, Charles Blundell, Timothy Lillicrap, Koray Kavukcuoglu, and Daan Wierstra. 2016. Matching networks for one shot learning. In Proceedings of the 30th International Conference on Neural Information Processing, Vol. 29, Curran Associates Inc., Red Hook, NY, 3637–3645.Google Scholar
- [64] Christopher Walker, Stephanie Strassel, Julie Medero, and Kazuaki Maeda. [n. d.]. ACE 2005 multilingual training corpus ldc2006t06, 2006. Google Scholar
Cross Ref
- [65] . 2019. Adversarial training for weakly supervised event detection. 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). Association for Computational Linguistics, Minneapolis, MN, 998–1008.
DOI: Google ScholarCross Ref
- [66] . 2021. CLEVE: Contrastive Pre-training for Event Extraction. arXiv:2105.14485 [cs.CL]Google Scholar
- [67] . 2020. Enhanced meta-learning for cross-lingual named entity recognition with minimal resources. In 34th AAAI Conference on Artificial Intelligence (AAAI’20). AAAI Press, 9274–9281. https://www.microsoft.com/en-us/research/publication/enhanced-meta-learning-for-cross-lingual-named-entity-recognition-with-minimal-resources/.Google Scholar
Cross Ref
- [68] . 2019. Beto, Bentz, Becas: The surprising cross-lingual effectiveness of BERT. arXiv:1904.09077 [cs.CL]Google Scholar
- [69] . 2016. Google’s neural machine translation system: Bridging the gap between human and machine translation. arXiv:1609.08144 [cs.CL]Google Scholar
- [70] . 2021. Event detection as graph parsing. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021. Association for Computational Linguistics, Online, 1630–1640.
DOI: Google ScholarCross Ref
- [71] . 2018. Neural cross-lingual named entity recognition with minimal resources. arXiv:1808.09861 [cs.CL]Google Scholar
- [72] . 2021. Document-level event extraction via heterogeneous graph-based interaction model with a tracker. arXiv:2105.14924 [cs.CL]Google Scholar
- [73] . 2019. Event detection with multi-order graph convolution and aggregated attention. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). Association for Computational Linguistics, Hong Kong, China, 5766–5770.
DOI: Google ScholarCross Ref
- [74] . 2019. Exploring pre-trained language models for event extraction and generation. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Florence, Italy, 5284–5294.
DOI: Google ScholarCross Ref
- [75] . 2020. Simple and effective few-shot named entity recognition with structured nearest neighbor learning. arXiv preprint arXiv:2010.02405Google Scholar
- [76] . 2014. Bilingual event extraction: A case study on trigger type determination. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). Association for Computational Linguistics, Baltimore, MD, 842–847.
DOI: Google ScholarCross Ref
Index Terms
Meta-ED: Cross-lingual Event Detection Using Meta-learning for Indian Languages
Recommendations
Cross-lingual word sense disambiguation for languages with scarce resources
Canadian AI'11: Proceedings of the 24th Canadian conference on Advances in artificial intelligenceWord Sense Disambiguation has long been a central problem in computational linguistics. Word Sense Disambiguation is the ability to identify the meaning of words in context in a computational manner. Statistical and supervised approaches require a large ...
Improving NER Tagging Performance in Low-Resource Languages via Multilingual Learning
Existing supervised solutions for Named Entity Recognition (NER) typically rely on a large annotated corpus. Collecting large amounts of NER annotated corpus is time-consuming and requires considerable human effort. However, collecting small amounts of ...
Unsupervised Cross-Lingual Sentence Representation Learning via Linguistic Isomorphism
Knowledge Science, Engineering and ManagementAbstractRecently, many researches on learning cross-lingual word embeddings without parallel data have achieved success by utilizing word isomorphism among languages. However, unsupervised cross-lingual sentence representation, which aims to learn a ...






Comments