{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,21]],"date-time":"2025-06-21T22:40:02Z","timestamp":1750545602231,"version":"3.41.0"},"publisher-location":"Cham","reference-count":60,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030791490"},{"type":"electronic","value":"9783030791506"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-79150-6_53","type":"book-chapter","created":{"date-parts":[[2021,6,21]],"date-time":"2021-06-21T23:35:17Z","timestamp":1624318517000},"page":"673-686","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Machine Learning Meets Natural Language Processing - The Story so Far"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9528-4349","authenticated-orcid":false,"given":"Nikolaos-Ioannis","family":"Galanis","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6448-5524","authenticated-orcid":false,"given":"Panagiotis","family":"Vafiadis","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4473-4631","authenticated-orcid":false,"given":"Kostas-Gkouram","family":"Mirzaev","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5545-1499","authenticated-orcid":false,"given":"George A.","family":"Papakostas","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,6,22]]},"reference":[{"key":"53_CR1","unstructured":"AllenNLP Github repository. https:\/\/github.com\/allenai\/allennlp. Accessed 21 Apr 2021"},{"key":"53_CR2","unstructured":"Common Crawl. https:\/\/commoncrawl.org\/. Accessed 21 Apr 2021"},{"key":"53_CR3","unstructured":"Eugene goostman. http:\/\/eugenegoostman.elasticbeanstalk.com\/. Accessed 21 Apr 2021"},{"key":"53_CR4","unstructured":"Flair Github repository. https:\/\/github.com\/flairNLP\/flair. Accessed 21 Apr 2021"},{"key":"53_CR5","unstructured":"Kaggle. https:\/\/www.kaggle.com\/. Accessed 21 Apr 2021"},{"key":"53_CR6","unstructured":"NLTK Github repository. https:\/\/github.com\/nltk\/nltk. Accessed 21 Apr 2021"},{"key":"53_CR7","unstructured":"spaCy Github repository. https:\/\/github.com\/explosion\/spaCy. Accessed 21 Apr 2021"},{"key":"53_CR8","unstructured":"SparkNLP Github repository. https:\/\/github.com\/JohnSnowLabs\/spark-nlp. Accessed 21 Apr 2021"},{"key":"53_CR9","unstructured":"Stanza Github repository. https:\/\/github.com\/stanfordnlp\/stanza Accessed 21 Apr 2021"},{"key":"53_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1007\/978-3-540-24630-5_55","volume-title":"Computational Linguistics and Intelligent Text Processing","author":"R Baeza-Yates","year":"2004","unstructured":"Baeza-Yates, R.: Challenges in the interaction of information retrieval and natural language processing. In: Gelbukh, A. (ed.) CICLing 2004. LNCS, vol. 2945, pp. 445\u2013456. Springer, Heidelberg (2004). https:\/\/doi.org\/10.1007\/978-3-540-24630-5_55"},{"key":"53_CR11","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)"},{"key":"53_CR12","unstructured":"Brown, K.: Encyclopedia of Language and Linguistics, vol. 1. Elsevier, Amsterdam (2005)"},{"key":"53_CR13","unstructured":"Brown, T.B., et al.: Language models are few-shot learners. arXiv preprint arXiv:2005.14165 (2020)"},{"issue":"3","key":"53_CR14","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1515\/humr.2004.013","volume":"17","author":"C Bucaria","year":"2004","unstructured":"Bucaria, C.: Lexical and syntactic ambiguity as a source of humor: the case of newspaper headlines. Humor 17(3), 279\u2013309 (2004)","journal-title":"Humor"},{"key":"53_CR15","doi-asserted-by":"crossref","unstructured":"Chen, Q., Zhu, X., Ling, Z., Wei, S., Jiang, H., Inkpen, D.: Enhanced LSTM for natural language inference. arXiv preprint arXiv:1609.06038 (2016)","DOI":"10.18653\/v1\/P17-1152"},{"key":"53_CR16","doi-asserted-by":"crossref","unstructured":"Conneau, A., et al.: Unsupervised cross-lingual representation learning at scale. arXiv preprint arXiv:1911.02116 (2019)","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"53_CR17","doi-asserted-by":"crossref","unstructured":"Dai, Z., Yang, Z., Yang, Y., Carbonell, J., Le, Q.V., Salakhutdinov, R.: Transformer-xl: Attentive language models beyond a fixed-length context. arXiv preprint arXiv:1901.02860 (2019)","DOI":"10.18653\/v1\/P19-1285"},{"key":"53_CR18","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"53_CR19","doi-asserted-by":"crossref","unstructured":"Dong, L., Wei, F., Zhou, M., Xu, K.: Question answering over freebase with multi-column 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), pp. 260\u2013269 (2015)","DOI":"10.3115\/v1\/P15-1026"},{"key":"53_CR20","unstructured":"Epstein, R., Roberts, G., Beber, G.: Parsing the Turing test. Springer, Berlin (2009)"},{"key":"53_CR21","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1613\/jair.4992","volume":"57","author":"Y Goldberg","year":"2016","unstructured":"Goldberg, Y.: A primer on neural network models for natural language processing. J. Artif. Intell. Res. 57, 345\u2013420 (2016)","journal-title":"J. Artif. Intell. Res."},{"key":"53_CR22","doi-asserted-by":"crossref","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"53_CR23","doi-asserted-by":"crossref","unstructured":"Howard, J., Ruder, S.: Universal language model fine-tuning for text classification. arXiv preprint arXiv:1801.06146 (2018)","DOI":"10.18653\/v1\/P18-1031"},{"key":"53_CR24","unstructured":"Jurafsky, D., Manning, C.: Natural language processing. Instructor 212(998), 3482 (2012)"},{"key":"53_CR25","doi-asserted-by":"crossref","unstructured":"Kalchbrenner, N., Grefenstette, E., Blunsom, P.: A convolutional neural network for modelling sentences. arXiv preprint arXiv:1404.2188 (2014)","DOI":"10.3115\/v1\/P14-1062"},{"key":"53_CR26","doi-asserted-by":"crossref","unstructured":"Kim, Y.: Convolutional neural networks for sentence classification (2014)","DOI":"10.3115\/v1\/D14-1181"},{"key":"53_CR27","doi-asserted-by":"crossref","unstructured":"Kurdi, M.Z.: Natural language processing and computational linguistics: speech, morphology and syntax, vol. 1, Wiley, Hoboken (2016)","DOI":"10.1002\/9781119145554"},{"key":"53_CR28","unstructured":"Lample, G., Conneau, A.: Cross-lingual language model pretraining. arXiv preprint arXiv:1901.07291 (2019)"},{"key":"53_CR29","unstructured":"Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., Soricut, R.: Albert: a lite bert for self-supervised learning of language representations. arXiv preprint arXiv:1909.11942 (2019)"},{"key":"53_CR30","doi-asserted-by":"crossref","unstructured":"Leech, G.N.: Principles of pragmatics. Routledge, London (2016)","DOI":"10.4324\/9781315835976"},{"key":"53_CR31","unstructured":"Liu, Y., et al.: Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"issue":"4","key":"53_CR32","doi-asserted-by":"publisher","first-page":"676","DOI":"10.1037\/0033-295X.101.4.676","volume":"101","author":"MC MacDonald","year":"1994","unstructured":"MacDonald, M.C., Pearlmutter, N.J., Seidenberg, M.S.: The lexical nature of syntactic ambiguity resolution. Psychol. Rev. 101(4), 676 (1994)","journal-title":"Psychol. Rev."},{"issue":"236","key":"53_CR33","first-page":"433","volume":"59","author":"C Machinery","year":"1950","unstructured":"Machinery, C.: Computing machinery and intelligence-am turing. Mind 59(236), 433 (1950)","journal-title":"Mind"},{"issue":"3","key":"53_CR34","first-page":"3236","volume":"5","author":"VR Mallamma","year":"2014","unstructured":"Mallamma, V.R., Hanumanthappa, M.: Semantical and syntactical analysis of NLP. Int. J. Comput. Sci. Inf. Technol. 5(3), 3236\u20133238 (2014)","journal-title":"Int. J. Comput. Sci. Inf. Technol."},{"key":"53_CR35","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013)"},{"key":"53_CR36","doi-asserted-by":"crossref","unstructured":"Mikolov, T., Kombrink, S., Burget, L., \u010cernock\u1ef3, J., Khudanpur, S.: Extensions of recurrent neural network language model. In: 2011 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp. 5528\u20135531. IEEE (2011)","DOI":"10.1109\/ICASSP.2011.5947611"},{"key":"53_CR37","unstructured":"Mikolov, T., Sutskever, I., Chen, K., Corrado, G., Dean, J.: Distributed representations of words and phrases and their compositionality. arXiv preprint arXiv:1310.4546 (2013)"},{"key":"53_CR38","doi-asserted-by":"publisher","first-page":"604","DOI":"10.1109\/TNNLS.2020.2979670","volume":"32","author":"DW Otter","year":"2020","unstructured":"Otter, D.W., Medina, J.R., Kalita, J.K.: A survey of the usages of deep learning for natural language processing. IEEE Trans. Neural Netw. Learn. Syst. 32, 604\u2013624 (2020)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"53_CR39","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: Glove: Global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"53_CR40","unstructured":"Peters, M.E., et al.: Deep contextualized word representations. arXiv preprint arXiv:1802.05365 (2018)"},{"key":"53_CR41","unstructured":"Pullum, G.: Philosophy of linguistics. The Cambridge Companion to History of Philosophy 2015, (1945)"},{"key":"53_CR42","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I.: Improving language understanding by generative pre-training (2018)"},{"issue":"8","key":"53_CR43","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners. OpenAI blog 1(8), 9 (2019)","journal-title":"OpenAI blog"},{"key":"53_CR44","unstructured":"Saenz, A.: Cleverbot chat engine is learning from the internet to talk like a human. Singularity Hub, Accessed 3 June 2021. https:\/\/singularityhub.com\/2010\/01\/13\/cleverbot-chat-engine-is-learning-from-the-internet-to-talk-like-a-human\/"},{"key":"53_CR45","unstructured":"Sanh, V., Debut, L., Chaumond, J., Wolf, T.: Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108 (2019)"},{"key":"53_CR46","doi-asserted-by":"crossref","unstructured":"Sarlin, P.E., DeTone, D., Malisiewicz, T., Rabinovich, A.: Superglue: Learning feature matching with graph neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer vision and Pattern Recognition, pp. 4938\u20134947 (2020)","DOI":"10.1109\/CVPR42600.2020.00499"},{"issue":"4","key":"53_CR47","doi-asserted-by":"publisher","first-page":"463","DOI":"10.1023\/A:1011288000451","volume":"10","author":"AP Saygin","year":"2000","unstructured":"Saygin, A.P., Cicekli, I., Akman, V.: Turing test: 50 years later. Minds Mach. 10(4), 463\u2013518 (2000)","journal-title":"Minds Mach."},{"key":"53_CR48","doi-asserted-by":"crossref","unstructured":"Strubell, E., Ganesh, A., McCallum, A.: Energy and policy considerations for deep learning in nlp. arXiv preprint arXiv:1906.02243 (2019)","DOI":"10.18653\/v1\/P19-1355"},{"key":"53_CR49","unstructured":"Sun, Y., et al.: Ernie: Enhanced representation through knowledge integration. arXiv preprint arXiv:1904.09223 (2019)"},{"key":"53_CR50","doi-asserted-by":"crossref","unstructured":"Sun, Y., et al.: Ernie 2.0: A continual pre-training framework for language understanding. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 8968\u20138975 (2020)","DOI":"10.1609\/aaai.v34i05.6428"},{"key":"53_CR51","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. arXiv preprint arXiv:1409.3215 (2014)"},{"key":"53_CR52","doi-asserted-by":"crossref","unstructured":"Upadhyay, S., Chang, K.W., Taddy, M., Kalai, A., Zou, J.: Beyond bilingual: Multi-sense word embeddings using multilingual context. arXiv preprint arXiv:1706.08160 (2017)","DOI":"10.18653\/v1\/W17-2613"},{"key":"53_CR53","unstructured":"Vaswani, A., et al.: Attention is all you need. arXiv preprint arXiv:1706.03762 (2017)"},{"key":"53_CR54","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1007\/3-540-39200-9_18","volume-title":"Advances in Cryptology \u2014 EUROCRYPT 2003","author":"L von Ahn","year":"2003","unstructured":"von Ahn, L., Blum, M., Hopper, N.J., Langford, J.: CAPTCHA: using hard AI problems for security. In: Biham, E. (ed.) EUROCRYPT 2003. LNCS, vol. 2656, pp. 294\u2013311. Springer, Heidelberg (2003). https:\/\/doi.org\/10.1007\/3-540-39200-9_18"},{"key":"53_CR55","doi-asserted-by":"crossref","unstructured":"Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., Bowman, S.R.: Glue: A multi-task benchmark and analysis platform for natural language understanding. arXiv preprint arXiv:1804.07461 (2018)","DOI":"10.18653\/v1\/W18-5446"},{"issue":"1","key":"53_CR56","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1145\/365153.365168","volume":"9","author":"J Weizenbaum","year":"1966","unstructured":"Weizenbaum, J.: Eliza-a computer program for the study of natural language communication between man and machine. Commun. ACM 9(1), 36\u201345 (1966)","journal-title":"Commun. ACM"},{"key":"53_CR57","unstructured":"Wolf, T., et al.: Huggingface\u2019s transformers: State-of-the-art natural language processing. arXiv preprint arXiv:1910.03771 (2019)"},{"key":"53_CR58","unstructured":"Yang, Z., Dai, Z., Yang, Y., Carbonell, J., Salakhutdinov, R., Le, Q.V.: Xlnet: Generalized autoregressive pretraining for language understanding. arXiv preprint arXiv:1906.08237 (2019)"},{"key":"53_CR59","unstructured":"Yin, W., Kann, K., Yu, M., Sch\u00fctze, H.: Comparative study of CNN and RNN for natural language processing. arXiv preprint arXiv:1702.01923 (2017)"},{"key":"53_CR60","doi-asserted-by":"crossref","unstructured":"Young, T., Hazarika, D., Poria, S., Cambria, E.: Recent trends in deep learning based natural language processing. IEEE Comput. Intell. Mag. 13(3), 55\u201375 (2018)","DOI":"10.1109\/MCI.2018.2840738"}],"container-title":["IFIP Advances in Information and Communication Technology","Artificial Intelligence Applications and Innovations"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-79150-6_53","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,21]],"date-time":"2025-06-21T22:03:36Z","timestamp":1750543416000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-79150-6_53"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030791490","9783030791506"],"references-count":60,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-79150-6_53","relation":{},"ISSN":["1868-4238","1868-422X"],"issn-type":[{"type":"print","value":"1868-4238"},{"type":"electronic","value":"1868-422X"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"22 June 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AIAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"IFIP International Conference on Artificial Intelligence Applications and Innovations","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hersonissos, Crete","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 June 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 June 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aiai2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.aiai2021.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"easyacademia.org","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"113","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"50","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"11","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"44% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.7","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.8","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}