{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T22:00:17Z","timestamp":1747173617493,"version":"3.40.5"},"reference-count":51,"publisher":"Cambridge University Press (CUP)","issue":"2","license":[{"start":{"date-parts":[[2022,2,4]],"date-time":"2022-02-04T00:00:00Z","timestamp":1643932800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/www.cambridge.org\/core\/terms"}],"content-domain":{"domain":["cambridge.org"],"crossmark-restriction":true},"short-container-title":["Nat. Lang. Eng."],"published-print":{"date-parts":[[2023,3]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Many fundamental tasks in natural language processing (NLP) such as part-of-speech tagging, text chunking, and named-entity recognition can be formulated as sequence labeling problems. Although neural sequence labeling models have shown excellent results on standard test sets, they are very brittle when presented with misspelled texts. In this paper, we introduce an adversarial training framework that enhances the robustness against typographical adversarial examples. We evaluate the robustness of sequence labeling models with an adversarial evaluation scheme that includes typographical adversarial examples. We generate two types of adversarial examples without access (black-box) or with full access (white-box) to the target model\u2019s parameters. We conducted a series of extensive experiments on three languages (English, Thai, and German) across three sequence labeling tasks. Experiments show that the proposed adversarial training framework provides better resistance against adversarial examples on all tasks. We found that we can further improve the model\u2019s robustness on the chunking task by including a triplet loss constraint.<\/jats:p>","DOI":"10.1017\/s1351324921000486","type":"journal-article","created":{"date-parts":[[2022,2,4]],"date-time":"2022-02-04T08:16:00Z","timestamp":1643962560000},"page":"287-315","update-policy":"https:\/\/doi.org\/10.1017\/policypage","source":"Crossref","is-referenced-by-count":0,"title":["Towards improving the robustness of sequential labeling models against typographical adversarial examples using triplet loss"],"prefix":"10.1017","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7090-0536","authenticated-orcid":false,"given":"Can","family":"Udomcharoenchaikit","sequence":"first","affiliation":[]},{"given":"Prachya","family":"Boonkwan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9718-3592","authenticated-orcid":false,"given":"Peerapon","family":"Vateekul","sequence":"additional","affiliation":[]}],"member":"56","published-online":{"date-parts":[[2022,2,4]]},"reference":[{"key":"S1351324921000486_ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-2006"},{"key":"S1351324921000486_ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"S1351324921000486_ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.609"},{"key":"S1351324921000486_ref37","doi-asserted-by":"publisher","DOI":"10.3115\/1596374.1596399"},{"key":"S1351324921000486_ref17","doi-asserted-by":"crossref","unstructured":"Jayanthi, S.M. , Pruthi, D. and Neubig, G. (2020). NeuSpell: A neural spelling correction toolkit. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 158\u2013164, Online. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2020.emnlp-demos.21"},{"key":"S1351324921000486_ref6","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00051"},{"key":"S1351324921000486_ref31","doi-asserted-by":"publisher","DOI":"10.1145\/2740908.2743039"},{"key":"S1351324921000486_ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"S1351324921000486_ref32","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273582"},{"key":"S1351324921000486_ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1527"},{"key":"S1351324921000486_ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1367"},{"key":"S1351324921000486_ref40","unstructured":"Sornlertlamvanich, V. , Takahashi, N. and Isahara, H. (1998). Thai part-of-speech tagged corpus: Orchid. In Proceedings of the Oriental COCOSDA Workshop, pp. 131\u2013138."},{"key":"S1351324921000486_ref14","unstructured":"Heigold, G. , Varanasi, S. , Neumann, G. and van Genabith, J. (2018). How robust are character-based word embeddings in tagging and MT against wrod scramlbing or randdm nouse? In Proceedings of the 13th Conference of the Association for Machine Translation in the Americas (Volume 1: Research Papers), Boston, MA. Association for Machine Translation in the Americas, pp. 68\u201380."},{"key":"S1351324921000486_ref34","unstructured":"Petrov, S. , Das, D. and McDonald, R. (2012). A universal part-of-speech tagset. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC\u201912), Istanbul, Turkey. European Language Resources Association (ELRA), pp. 2089\u20132096."},{"key":"S1351324921000486_ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1326"},{"key":"S1351324921000486_ref7","unstructured":"Devlin, J. , Chang, M.-W. , Lee, K. and Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. 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), Minneapolis, Minnesota. Association for Computational Linguistics, pp. 4171\u20134186."},{"key":"S1351324921000486_ref45","doi-asserted-by":"publisher","DOI":"10.1109\/SNLP.2009.5340913"},{"key":"S1351324921000486_ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"S1351324921000486_ref43","unstructured":"Telljohann, H. , Hinrichs, E. , K\u00dcbler, S. and K\u00dcbler, R. (2004). The t\u00dcba-d\/z treebank: Annotating german with a context-free backbone. In In Proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC 2004). Citeseer."},{"key":"S1351324921000486_ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1279"},{"key":"S1351324921000486_ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1027"},{"key":"S1351324921000486_ref27","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-1126"},{"key":"S1351324921000486_ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1221"},{"key":"S1351324921000486_ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1215"},{"key":"S1351324921000486_ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6356"},{"key":"S1351324921000486_ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1030"},{"key":"S1351324921000486_ref30","unstructured":"Miyato, T. , Dai, A.M. and Goodfellow, I.J. (2017). Adversarial training methods for semi-supervised text classification. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings. OpenReview.net."},{"key":"S1351324921000486_ref2","unstructured":"Akbik, A. , Blythe, D. and Vollgraf, R. (2018). Contextual string embeddings for sequence labeling. In Proceedings of the 27th International Conference on Computational Linguistics, pp. 1638\u20131649, Santa Fe, New Mexico, USA. Association for Computational Linguistics."},{"key":"S1351324921000486_ref16","unstructured":"Huang, Z. , Xu, W. and Yu, K. (2015). Bidirectional LSTM-CRF models for sequence tagging. CoRR, abs\/1508.01991."},{"key":"S1351324921000486_ref13","unstructured":"Goodfellow, I. , Shlens, J. and Szegedy, C. (2015). Explaining and harnessing adversarial examples. In International Conference on Learning Representations."},{"key":"S1351324921000486_ref3","unstructured":"Belinkov, Y. and Bisk, Y. (2018). Synthetic and natural noise both break neural machine translation. In International Conference on Learning Representations."},{"key":"S1351324921000486_ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1604"},{"key":"S1351324921000486_ref42","unstructured":"Szegedy, C. , Zaremba, W. , Sutskever, I. , Bruna, J. , Erhan, D. , Goodfellow, I. and Fergus, R. (2014). Intriguing properties of neural networks. In International Conference on Learning Representations."},{"key":"S1351324921000486_ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-2501"},{"key":"S1351324921000486_ref47","doi-asserted-by":"publisher","DOI":"10.1197\/jamia.M2444"},{"key":"S1351324921000486_ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1089"},{"key":"S1351324921000486_ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2911236"},{"key":"S1351324921000486_ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-5531"},{"key":"S1351324921000486_ref4","doi-asserted-by":"publisher","DOI":"10.3765\/bls.v21i2.1384"},{"key":"S1351324921000486_ref46","doi-asserted-by":"publisher","DOI":"10.3115\/1119176.1119195"},{"key":"S1351324921000486_ref44","unstructured":"Telljohann, H. , Hinrichs, E.W. , K\u00dcbler, S. , Zinsmeister, H. and Beck, K. (2005). Stylebook for the t\u00dcbingen treebank of written german (t\u00dcba-d\/z). In Seminar f\u00dcr Sprachwissenschaft, Universit\u00e4t T\u00fcbingen, Germany."},{"key":"S1351324921000486_ref26","article-title":"De-identification of clinical notes via recurrent neural network and conditional random field","volume":"75","author":"Liu","year":"2017","journal-title":"Supplement: A Natural Language Processing Challenge for Clinical Records: Research Domains Criteria (RDoC) for Psychiatry."},{"key":"S1351324921000486_ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1078"},{"key":"S1351324921000486_ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SPW.2018.00016"},{"key":"S1351324921000486_ref11","unstructured":"Gardner, M. , Artzi, Y. , Basmova, V. , Berant, J. , Bogin, B. , Chen, S. , Dasigi, P. , Dua, D. , Elazar, Y. , Gottumukkala, A. , et al. (2020). Evaluating nlp models via contrast sets. arXiv preprint arXiv:2004.02709."},{"key":"S1351324921000486_ref29","doi-asserted-by":"publisher","DOI":"10.1177\/0539018410389107"},{"key":"S1351324921000486_ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1561"},{"key":"S1351324921000486_ref22","unstructured":"Lafferty, J.D. , McCallum, A. and Pereira, F.C.N. (2001). Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In Proceedings of the Eighteenth International Conference on Machine Learning, ICML \u201901, San Francisco, CA, USA. Morgan Kaufmann Publishers Inc, 282\u2013289."},{"key":"S1351324921000486_ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1176"},{"key":"S1351324921000486_ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1314"},{"key":"S1351324921000486_ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-5506"}],"container-title":["Natural Language Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.cambridge.org\/core\/services\/aop-cambridge-core\/content\/view\/S1351324921000486","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,13]],"date-time":"2023-03-13T04:19:53Z","timestamp":1678681193000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.cambridge.org\/core\/product\/identifier\/S1351324921000486\/type\/journal_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,4]]},"references-count":51,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2023,3]]}},"alternative-id":["S1351324921000486"],"URL":"https:\/\/doi.org\/10.1017\/s1351324921000486","relation":{},"ISSN":["1351-3249","1469-8110"],"issn-type":[{"type":"print","value":"1351-3249"},{"type":"electronic","value":"1469-8110"}],"subject":[],"published":{"date-parts":[[2022,2,4]]},"assertion":[{"value":"\u00a9 The Author(s), 2022. Published by Cambridge University Press","name":"copyright","label":"Copyright","group":{"name":"copyright_and_licensing","label":"Copyright and Licensing"}}]}}