{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T19:59:30Z","timestamp":1775246370575,"version":"3.50.1"},"publisher-location":"Cham","reference-count":104,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319771120","type":"print"},{"value":"9783319771137","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-319-77113-7_1","type":"book-chapter","created":{"date-parts":[[2018,10,9]],"date-time":"2018-10-09T07:14:48Z","timestamp":1539069288000},"page":"3-16","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Overview of Character-Based Models for Natural Language Processing"],"prefix":"10.1007","author":[{"given":"Heike","family":"Adel","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ehsaneddin","family":"Asgari","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hinrich","family":"Sch\u00fctze","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,10,10]]},"reference":[{"key":"1_CR1","doi-asserted-by":"crossref","unstructured":"Alex, B.: An unsupervised system for identifying english inclusions in german text. In: Annual Meeting of the Association for Computational Linguistics (2005)","DOI":"10.3115\/1628960.1628985"},{"key":"1_CR2","doi-asserted-by":"crossref","unstructured":"Andor, D., et al.: Globally normalized transition-based neural networks. In: Annual Meeting of the Association for Computational Linguistics (2016)","DOI":"10.18653\/v1\/P16-1231"},{"issue":"11","key":"1_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pone.0141287","volume":"10","author":"E Asgari","year":"2015","unstructured":"Asgari, E., Mofrad, M.R.K.: Continuous distributed representation of biological sequences for deep proteomics and genomics. PLoS ONE 10(11), 1\u201315 (2015)","journal-title":"PLoS ONE"},{"key":"1_CR4","doi-asserted-by":"crossref","unstructured":"Asgari, E., Mofrad, M.R.K.: Comparing fifty natural languages and twelve genetic languages using word embedding language divergence (WELD) as a quantitative measure of language distance. In: Workshop on Multilingual and Cross-lingual Methods in NLP, pp. 65\u201374 (2016)","DOI":"10.18653\/v1\/W16-1208"},{"key":"1_CR5","doi-asserted-by":"crossref","unstructured":"Bahdanau, D., Chorowski, J., Serdyuk, D., Brakel, P., Bengio, Y.: End-to-end attention-based large vocabulary speech recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 4945\u20134949 (2016)","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"1_CR6","unstructured":"Baldwin, T., Lui, M.: Language identification: the long and the short of the matter. In: Conference of the North American Chapter of the Association for Computational Linguistics\/Human Language Technologies, pp. 229\u2013237 (2010)"},{"key":"1_CR7","doi-asserted-by":"crossref","unstructured":"Ballesteros, M., Dyer, C., Smith, N.A.: Improved transition-based parsing by modeling characters instead of words with LSTMS. In: Conference on Empirical Methods in Natural Language Processing (2015)","DOI":"10.18653\/v1\/D15-1041"},{"key":"1_CR8","doi-asserted-by":"crossref","unstructured":"Bilmes, J., Kirchhoff, K.: Factored language models and generalized parallel backoff. In: Conference of the North American Chapter of the Association for Computational Linguistics\/Human Language Technologies (2003)","DOI":"10.3115\/1073483.1073485"},{"issue":"5","key":"1_CR9","doi-asserted-by":"publisher","first-page":"434","DOI":"10.1016\/j.specom.2008.01.002","volume":"50","author":"M Bisani","year":"2008","unstructured":"Bisani, M., Ney, H.: Joint-sequence models for grapheme-to-phoneme conversion. Speech Commun. 50(5), 434\u2013451 (2008)","journal-title":"Speech Commun."},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"Bojanowski, P., Grave, E., Joulin, A., Mikolov, T.: Enriching word vectors with subword information. Transactions of the Association for Computational Linguistics (2017)","DOI":"10.1162\/tacl_a_00051"},{"key":"1_CR11","unstructured":"Bojanowski, P., Joulin, A., Mikolov, T.: Alternative structures for character-level RNNS. In: Workshop at International Conference on Learning Representations (2016)"},{"key":"1_CR12","unstructured":"Botha, J.A., Blunsom, P.: Compositional morphology for word representations and language modelling. In: International Conference on Machine Learning (2014)"},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"Cao, K., Rei, M.: A joint model for word embedding and word morphology. In: Annual Meeting of the Association for Computational Linguistics, pp. 18\u201326 (2016)","DOI":"10.18653\/v1\/W16-1603"},{"key":"1_CR14","unstructured":"Cavnar, W.: Using an n-gram-based document representation with a vector processing retrieval model. NIST SPECIAL PUBLICATION SP, pp. 269\u2013269 (1995)"},{"key":"1_CR15","doi-asserted-by":"crossref","unstructured":"Chan, W., Jaitly, N., Le, Q.V., Vinyals, O.: Listen, attend and spell: A neural network for large vocabulary conversational speech recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 4960\u20134964 (2016)","DOI":"10.1109\/ICASSP.2016.7472621"},{"issue":"SI","key":"1_CR16","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1145\/278459.258532","volume":"31","author":"A Chen","year":"1997","unstructured":"Chen, A., He, J., Xu, L., Gey, F.C., Meggs, J.: Chinese text retrieval without using a dictionary. ACM SIGIR Forum 31(SI), 42\u201349 (1997)","journal-title":"ACM SIGIR Forum"},{"key":"1_CR17","unstructured":"Chen, X., Xu, L., Liu, Z., Sun, M., Luan, H.: Joint learning of character and word embeddings. In: International Joint Conference on Artificial Intelligence, pp. 1236\u20131242 (2015)"},{"key":"1_CR18","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1162\/tacl_a_00104","volume":"4","author":"JPC Chiu","year":"2016","unstructured":"Chiu, J.P.C., Nichols, E.: Named entity recognition with bidirectional LSTM-CNNS. Trans. Assoc. Comput. Linguist. 4, 357\u2013370 (2016)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"1_CR19","unstructured":"Chung, J., Ahn, S., Bengio, Y.: Hierarchical multiscale recurrent neural networks. In: Proceedings of International Conference on Learning Representations (2017)"},{"key":"1_CR20","doi-asserted-by":"crossref","unstructured":"Chung, J., Cho, K., Bengio, Y.: A character-level decoder without explicit segmentation for neural machine translation. In: Annual Meeting of the Association for Computational Linguistics (2016)","DOI":"10.18653\/v1\/P16-1160"},{"key":"1_CR21","doi-asserted-by":"crossref","unstructured":"Church, K.W.: Char$$\\_$$align: a program for aligning parallel texts at the character level. In: Annual Meeting of the Association for Computational Linguistics, pp. 1\u20138 (1993)","DOI":"10.3115\/981574.981575"},{"key":"1_CR22","doi-asserted-by":"crossref","unstructured":"Clark, A.: Combining distributional and morphological information for part of speech induction. In: Conference of the European Chapter of the Association for Computational Linguistics, pp. 59\u201366 (2003)","DOI":"10.3115\/1067807.1067817"},{"key":"1_CR23","first-page":"2493","volume":"12","author":"R Collobert","year":"2011","unstructured":"Collobert, R., Weston, J., Bottou, L., Karlen, M., Kavukcuoglu, K., Kuksa, P.: Natural language processing (almost) from scratch. J. Mach. Learn. Res. 12, 2493\u20132537 (2011)","journal-title":"J. Mach. Learn. Res."},{"key":"1_CR24","doi-asserted-by":"crossref","unstructured":"Costa-Juss\u00e0, M.R., Fonollosa, J.A.R.: Character-based neural machine translation. In: Annual Meeting of the Association for Computational Linguistics (2016)","DOI":"10.18653\/v1\/P16-2058"},{"key":"1_CR25","doi-asserted-by":"crossref","unstructured":"Cotterell, R., Vieira, T., Sch\u00fctze, H.: A joint model of orthography and morphological segmentation. In: Conference of the North American Chapter of the Association for Computational Linguistics\/Human Language Technologies (2016)","DOI":"10.18653\/v1\/N16-1080"},{"key":"1_CR26","doi-asserted-by":"publisher","first-page":"843","DOI":"10.1126\/science.267.5199.843","volume":"267","author":"M Damashek","year":"1995","unstructured":"Damashek, M.: Gauging similarity with n-grams: language-independent categorization of text. Science 267, 843\u2013848 (1995)","journal-title":"Science"},{"issue":"3\u20134","key":"1_CR27","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1016\/0020-0271(74)90015-1","volume":"10","author":"T Heer De","year":"1974","unstructured":"De Heer, T.: Experiments with syntactic traces in information retrieval. Inf. Storage Retr. 10(3\u20134), 133\u2013144 (1974)","journal-title":"Inf. Storage Retr."},{"key":"1_CR28","unstructured":"Dunning, T.: Statistical identification of language. Technical Report MCCS 940\u2013273, Computing Research Laboratory, New Mexico State (1994)"},{"key":"1_CR29","doi-asserted-by":"crossref","unstructured":"Eyben, F., W\u00f6llmer, M., Schuller, B.W., Graves, A.: From speech to letters - using a novel neural network architecture for grapheme based ASR. In: IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU), pp. 376\u2013380 (2009)","DOI":"10.1109\/ASRU.2009.5373257"},{"key":"1_CR30","doi-asserted-by":"crossref","unstructured":"Eyecioglu, A., Keller, B.: ASOBEK at SemEval-2016 task 1: sentence representation with character n-gram embeddings for semantic textual similarity. In: SemEval-2016: The 10th International Workshop on Semantic Evaluation, pp. 1320\u20131324 (2016)","DOI":"10.18653\/v1\/S16-1114"},{"key":"1_CR31","doi-asserted-by":"crossref","unstructured":"Faruqui, M., Tsvetkov, Y., Neubig, G., Dyer, C.: Morphological inflection generation using character sequence to sequence learning. In: Conference of the North American Chapter of the Association for Computational Linguistics\/Human Language Technologies (2016)","DOI":"10.18653\/v1\/N16-1077"},{"key":"1_CR32","unstructured":"Gerdjikov, S., Schulz, K.U.: Corpus analysis without prior linguistic knowledge-unsupervised mining of phrases and subphrase structure. CoRR abs\/1602.05772 (2016)"},{"key":"1_CR33","doi-asserted-by":"crossref","unstructured":"Gillick, D., Brunk, C., Vinyals, O., Subramanya, A.: Multilingual language processing from bytes. In: North American Chapter of the Association for Computational Linguistics, pp. 1296\u20131306, June 2016","DOI":"10.18653\/v1\/N16-1155"},{"key":"1_CR34","unstructured":"Golub, D., He, X.: Character-level question answering with attention. In: Conference on Empirical Methods in Natural Language Processing (2016)"},{"key":"1_CR35","unstructured":"Graves, A.: Generating sequences with recurrent neural networks. CoRR abs\/1308.0850 (2013)"},{"key":"1_CR36","unstructured":"Graves, A., Jaitly, N.: Towards end-to-end speech recognition with recurrent neural networks. In: International Conference on Machine Learning, pp. 1764\u20131772 (2014)"},{"key":"1_CR37","doi-asserted-by":"crossref","unstructured":"Haizhou, L., Min, Z., Jian, S.: A joint source-channel model for machine transliteration. In: Annual Meeting of the Association for Computational Linguistics, p. 159 (2004)","DOI":"10.3115\/1218955.1218976"},{"key":"1_CR38","unstructured":"Hardmeier, C.: A neural model for part-of-speech tagging in historical texts. In: International Conference on Computational Linguistics, pp. 922\u2013931 (2016)"},{"issue":"4","key":"1_CR39","doi-asserted-by":"publisher","first-page":"515","DOI":"10.1016\/j.csl.2005.07.002","volume":"20","author":"T Hirsim\u00e4ki","year":"2006","unstructured":"Hirsim\u00e4ki, T., Creutz, M., Siivola, V., Kurimo, M., Virpioja, S., Pylkk\u00f6nen, J.: Unlimited vocabulary speech recognition with morph language models applied to finnish. Comput. Speech Lang. 20(4), 515\u2013541 (2006)","journal-title":"Comput. Speech Lang."},{"key":"1_CR40","doi-asserted-by":"crossref","unstructured":"Ircing, P., et al.: On large vocabulary continuous speech recognition of highly inflectional language-czech. In: Proceedings of the 7th European Conference on Speech Communication and Technology, vol. 1, pp. 487\u2013490. ISCA: International Speech Communication Association (2001)","DOI":"10.21437\/Eurospeech.2001-128"},{"key":"1_CR41","doi-asserted-by":"crossref","unstructured":"Jaech, A., Mulcaire, G., Hathi, S., Ostendorf, M., Smith, N.A.: Hierarchical character-word models for language identification. In: Proceedings of The Fourth International Workshop on Natural Language Processing for Social Media, pp. 84\u201393 (2016)","DOI":"10.18653\/v1\/W16-6212"},{"key":"1_CR42","unstructured":"Kalchbrenner, N., Espeholt, L., Simonyan, K., van den Oord, A., Graves, A., Kavukcuoglu, K.: Neural machine translation in linear time. CoRR abs\/1610.10099 (2016)"},{"key":"1_CR43","doi-asserted-by":"crossref","unstructured":"Kann, K., Cotterell, R., Sch\u00fctze, H.: Neural morphological analysis: encoding-decoding canonical segments. In: Conference on Empirical Methods in Natural Language Processing (2016)","DOI":"10.18653\/v1\/D16-1097"},{"key":"1_CR44","doi-asserted-by":"crossref","unstructured":"Kann, K., Sch\u00fctze, H.: MED: The LMU system for the SIGMORPHON 2016 shared task on morphological reinflection. In: SIGMORPHON Workshop (2016)","DOI":"10.18653\/v1\/W16-2010"},{"key":"1_CR45","doi-asserted-by":"crossref","unstructured":"Kann, K., Sch\u00fctze, H.: Single-model encoder-decoder with explicit morphological representation for reinflection. In: Annual Meeting of the Association for Computational Linguistics (2016)","DOI":"10.18653\/v1\/P16-2090"},{"issue":"3","key":"1_CR46","first-page":"331","volume":"20","author":"RM Kaplan","year":"1994","unstructured":"Kaplan, R.M., Kay, M.: Regular models of phonological rule systems. Comput. Linguist. 20(3), 331\u2013378 (1994)","journal-title":"Comput. Linguist."},{"key":"1_CR47","unstructured":"Kettunen, K., McNamee, P., Baskaya, F.: Using syllables as indexing terms in full-text information retrieval. In: Human Language Technologies - The Baltic Perspective - Proceedings of the Fourth International Conference Baltic HLT 2010, Riga, Latvia, October 7\u20138, 2010, pp. 225\u2013232 (2010)"},{"key":"1_CR48","doi-asserted-by":"crossref","unstructured":"Kim, Y., Jernite, Y., Sontag, D., Rush, A.M.: Character-aware neural language models. In: AAAI Conference on Artificial Intelligence, pp. 2741\u20132749 (2016)","DOI":"10.1609\/aaai.v30i1.10362"},{"issue":"4","key":"1_CR49","doi-asserted-by":"publisher","first-page":"589","DOI":"10.1016\/j.csl.2005.10.001","volume":"20","author":"K Kirchhoff","year":"2006","unstructured":"Kirchhoff, K., Vergyri, D., Bilmes, J., Duh, K., Stolcke, A.: Morphology-based language modeling for conversational arabic speech recognition. Comput. Speech Lang. 20(4), 589\u2013608 (2006)","journal-title":"Comput. Speech Lang."},{"key":"1_CR50","doi-asserted-by":"crossref","unstructured":"Klein, D., Smarr, J., Nguyen, H., Manning, C.D.: Named entity recognition with character-level models. In: Computational Natural Language Learning, pp. 180\u2013183 (2003)","DOI":"10.3115\/1119176.1119204"},{"issue":"4","key":"1_CR51","first-page":"599","volume":"24","author":"K Knight","year":"1998","unstructured":"Knight, K., Graehl, J.: Machine transliteration. Comput. Linguist. 24(4), 599\u2013612 (1998)","journal-title":"Comput. Linguist."},{"key":"1_CR52","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1007\/978-3-319-45510-5_21","volume-title":"Text, Speech, and Dialogue","author":"T Kocmi","year":"2016","unstructured":"Kocmi, T., Bojar, O.: SubGram: extending skip-gram word representation with substrings. In: Sojka, P., Hor\u00e1k, A., Kope\u010dek, I., Pala, K. (eds.) TSD 2016. LNCS (LNAI), vol. 9924, pp. 182\u2013189. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-45510-5_21"},{"key":"1_CR53","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"330","DOI":"10.1007\/978-3-642-15760-8_42","volume-title":"Text, Speech and Dialogue","author":"S Kombrink","year":"2010","unstructured":"Kombrink, S., Hannemann, M., Burget, L., He\u0159mansk\u00fd, H.: Recovery of rare words in lecture speech. In: Sojka, P., Hor\u00e1k, A., Kope\u010dek, I., Pala, K. (eds.) TSD 2010. LNCS (LNAI), vol. 6231, pp. 330\u2013337. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15760-8_42"},{"key":"1_CR54","doi-asserted-by":"crossref","unstructured":"Kou, W., Li, F., Baldwin, T.: Automatic labelling of topic models using word vectors and letter trigram vectors. In: Asia Information Retrieval Societies Conference (AIRS), pp. 253\u2013264 (2015)","DOI":"10.1007\/978-3-319-28940-3_20"},{"key":"1_CR55","doi-asserted-by":"crossref","unstructured":"Lample, G., Ballesteros, M., Subramanian, S., Kawakami, K., Dyer, C.: Neural architectures for named entity recognition. In: Conference of the North American Chapter of the Association for Computational Linguistics\/Human Language Technologies (2016)","DOI":"10.18653\/v1\/N16-1030"},{"key":"1_CR56","unstructured":"Lee, J., Cho, K., Hofmann, T.: Fully character-level neural machine translation without explicit segmentation. CoRR abs\/1610.03017 (2016)"},{"issue":"3\u20134","key":"1_CR57","first-page":"251","volume":"19","author":"Y Lepage","year":"2005","unstructured":"Lepage, Y., Denoual, E.: Purest ever example-based machine translation: detailed presentation and assessment. Mach. Transl. 19(3\u20134), 251\u2013282 (2005)","journal-title":"Mach. Transl."},{"key":"1_CR58","doi-asserted-by":"crossref","unstructured":"Ling, W., et al.: Finding function in form: compositional character models for open vocabulary word representation. In: Conference on Empirical Methods in Natural Language Processing, pp. 1520\u20131530 (2015)","DOI":"10.18653\/v1\/D15-1176"},{"key":"1_CR59","unstructured":"Ling, W., Trancoso, I., Dyer, C., Black, A.W.: Character-based neural machine translation. CoRR abs\/1511.04586 (2015)"},{"key":"1_CR60","doi-asserted-by":"crossref","unstructured":"Luong, M., Manning, C.D.: Achieving open vocabulary neural machine translation with hybrid word-character models. In: Annual Meeting of the Association for Computational Linguistics (2016)","DOI":"10.18653\/v1\/P16-1100"},{"key":"1_CR61","unstructured":"Luong, M.T., Socher, R., Manning, C.D.: Better word representations with recursive neural networks for morphology. In: Computational Natural Language Learning (2013)"},{"key":"1_CR62","doi-asserted-by":"crossref","unstructured":"Ma, X., Hovy, E.H.: End-to-end sequence labeling via bi-directional LSTM-CNNS-CRF. In: Annual Meeting of the Association for Computational Linguistics (2016)","DOI":"10.18653\/v1\/P16-1101"},{"issue":"1\u20132","key":"1_CR63","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1023\/B:INRT.0000009441.78971.be","volume":"7","author":"P McNamee","year":"2004","unstructured":"McNamee, P., Mayfield, J.: Character n-gram tokenization for european language text retrieval. Inf. Retr. 7(1\u20132), 73\u201397 (2004)","journal-title":"Inf. Retr."},{"key":"1_CR64","doi-asserted-by":"crossref","unstructured":"Mihalcea, R., Nastase, V.: Letter level learning for language independent diacritics restoration. In: Computational Natural Language Learning (2002)","DOI":"10.3115\/1118853.1118874"},{"key":"1_CR65","unstructured":"Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Advances in Neural Information Processing Systems, pp. 3111\u20133119 (2013)"},{"key":"1_CR66","unstructured":"Mikolov, T., Sutskever, I., Deoras, A., Le, H.S., Kombrink, S., Cernocky, J.: Subword language modeling with neural networks (2012)"},{"key":"1_CR67","doi-asserted-by":"crossref","unstructured":"Miyamoto, Y., Cho, K.: Gated word-character recurrent language model. In: Conference on Empirical Methods in Natural Language Processing, pp. 1992\u20131997 (2016)","DOI":"10.18653\/v1\/D16-1209"},{"key":"1_CR68","doi-asserted-by":"crossref","unstructured":"M\u00fcller, T., Schmid, H., Sch\u00fctze, H.: Efficient higher-order CRFs for morphological tagging. In: Conference on Empirical Methods in Natural Language Processing, pp. 322\u2013332 (2013)","DOI":"10.18653\/v1\/D13-1032"},{"key":"1_CR69","unstructured":"Parada, C., Dredze, M., Sethy, A., Rastrow, A.: Learning sub-word units for open vocabulary speech recognition. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, vol. 1, pp. 712\u2013721 (2011)"},{"key":"1_CR70","doi-asserted-by":"crossref","unstructured":"Peng, F., Schuurmans, D., Wang, S., Keselj, V.: Language independent authorship attribution using character level language models. In: Conference of the European Chapter of the Association for Computational Linguistics, pp. 267\u2013274 (2003)","DOI":"10.3115\/1067807.1067843"},{"key":"1_CR71","doi-asserted-by":"crossref","unstructured":"Pettersson, E., Megyesi, B., Nivre, J.: A multilingual evaluation of three spelling normalisation methods for historical text. In: Proceedings of the 8th Workshop on Language Technology for Cultural Heritage, Social Sciences, and Humanities, pp. 32\u201341 (2014)","DOI":"10.3115\/v1\/W14-0605"},{"key":"1_CR72","doi-asserted-by":"crossref","unstructured":"Plank, B., S\u00f8gaard, A., Goldberg, Y.: Multilingual part-of-speech tagging with bidirectional long short-term memory models and auxiliary loss. In: Annual Meeting of the Association for Computational Linguistics (2016)","DOI":"10.18653\/v1\/P16-2067"},{"key":"1_CR73","doi-asserted-by":"crossref","unstructured":"Rastogi, P., Cotterell, R., Eisner, J.: Weighting finite-state transductions with neural context. In: Conference of the North American Chapter of the Association for Computational Linguistics\/Human Language Technologies, pp. 623\u2013633 (2016)","DOI":"10.18653\/v1\/N16-1076"},{"key":"1_CR74","unstructured":"Ratnaparkhi, A., et al.: A maximum entropy model for part-of-speech tagging. In: Conference on Empirical Methods in Natural Language Processing, vol. 1, pp. 133\u2013142. Philadelphia, USA (1996)"},{"key":"1_CR75","unstructured":"Sajjad, H.: Statistical models for unsupervised, semi-supervised and supervised transliteration mining. In: Computational Linguistics (2012)"},{"key":"1_CR76","unstructured":"dos Santos, C.N., Gatti, M.: Deep convolutional neural networks for sentiment analysis of short texts. In: International Conference on Computational Linguistics. pp. 69\u201378 (2014)"},{"key":"1_CR77","doi-asserted-by":"crossref","unstructured":"dos Santos, C.N., Guimar\u00e3es, V.: Boosting named entity recognition with neural character embeddings. In: Fifth Named Entity Workshop, pp. 25\u201333 (2015)","DOI":"10.18653\/v1\/W15-3904"},{"key":"1_CR78","unstructured":"dos Santos, C.N., Zadrozny, B.: Learning character-level representations for part-of-speech tagging. In: International Conference on Machine Learning, pp. 1818\u20131826 (2014)"},{"key":"1_CR79","unstructured":"Sch\u00fctze, H.: Word space. In: Advances in Neural Information Processing Systems, pp. 895\u2013902 (1992)"},{"key":"1_CR80","unstructured":"Sch\u00fctze, H.: Nonsymbolic text representation. CoRR abs\/1610.00479 (2016)"},{"issue":"1","key":"1_CR81","first-page":"145","volume":"1","author":"TJ Sejnowski","year":"1987","unstructured":"Sejnowski, T.J., Rosenberg, C.R.: Parallel networks that learn to pronounce english text. Complex Syst. 1(1), 145\u2013168 (1987)","journal-title":"Complex Syst."},{"key":"1_CR82","doi-asserted-by":"crossref","unstructured":"Sennrich, R., Haddow, B., Birch, A.: Neural machine translation of rare words with subword units. In: Annual Meeting of the Association for Computational Linguistics (2016)","DOI":"10.18653\/v1\/P16-1162"},{"key":"1_CR83","doi-asserted-by":"crossref","unstructured":"Shaik, M.A.B., Mousa, A.E.D., Schl\u00fcter, R., Ney, H.: Hybrid language models using mixed types of sub-lexical units for open vocabulary german lvcsr. In: Annual Conference of the International Speech Communication Association, pp. 1441\u20131444 (2011)","DOI":"10.21437\/Interspeech.2011-252"},{"key":"1_CR84","doi-asserted-by":"crossref","unstructured":"Shaik, M.A.B., Mousa, A.E., Schl\u00fcter, R., Ney, H.: Feature-rich sub-lexical language models using a maximum entropy approach for german LVCSR. In: Annual Conference of the International Speech Communication Association, pp. 3404\u20133408 (2013)","DOI":"10.21437\/Interspeech.2013-746"},{"issue":"1","key":"1_CR85","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1002\/j.1538-7305.1951.tb01366.x","volume":"30","author":"CE Shannon","year":"1951","unstructured":"Shannon, C.E.: Prediction and entropy of printed english. Bell Labs Tech. J. 30(1), 50\u201364 (1951)","journal-title":"Bell Labs Tech. J."},{"key":"1_CR86","unstructured":"Sperr, H., Niehues, J., Waibel, A.: Letter n-gram-based input encoding for continuous space language models. In: Workshop on Continuous Vector Space Models and their Compositionality, pp. 30\u201339 (2013)"},{"key":"1_CR87","unstructured":"Srivastava, R.K., Greff, K., Schmidhuber, J.: Highway networks. In: ICML 2015 Deep Learing Workshop (2015)"},{"key":"1_CR88","unstructured":"Sutskever, I., Martens, J., Hinton, G.E.: Generating text with recurrent neural networks. In: International Conference on Machine Learning, pp. 1017\u20131024 (2011)"},{"key":"1_CR89","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Advances in Neural Information Processing Systems, pp. 3104\u20133112 (2014)"},{"key":"1_CR90","unstructured":"Tiedemann, J., Nakov, P.: Analyzing the use of character-level translation with sparse and noisy datasets. In: Recent Advances in Natural Language Processing, RANLP 2013, 9\u201311 September, 2013, Hissar, Bulgaria, pp. 676\u2013684 (2013)"},{"key":"1_CR91","unstructured":"Murthy, V., Khapra, M.M., Bhattacharyya, P.: Sharing network parameters for crosslingual named entity recognition. CoRR abs\/1607.00198 (2016)"},{"key":"1_CR92","doi-asserted-by":"crossref","unstructured":"Vergyri, D., Kirchhoff, K., Duh, K., Stolcke, A.: Morphology-based language modeling for arabic speech recognition. In: Annual Conference of the International Speech Communication Association, 4, 2245\u20132248 (2004)","DOI":"10.21437\/Interspeech.2004-495"},{"key":"1_CR93","doi-asserted-by":"crossref","unstructured":"Vilar, D., Peter, J.T., Ney, H.: Can we translate letters? In: Workshop on Statistical Machine Translation (2007)","DOI":"10.3115\/1626355.1626360"},{"key":"1_CR94","doi-asserted-by":"crossref","unstructured":"Vylomova, E., Cohn, T., He, X., Haffari, G.: Word representation models for morphologically rich languages in neural machine translation. CoRR abs\/1606.04217 (2016)","DOI":"10.18653\/v1\/W17-4115"},{"key":"1_CR95","doi-asserted-by":"crossref","unstructured":"Wang, L., Cao, Z., Xia, Y., de Melo, G.: Morphological segmentation with window LSTM neural networks. In: AAAI Conference on Artificial Intelligence (2016)","DOI":"10.1609\/aaai.v30i1.10363"},{"key":"1_CR96","doi-asserted-by":"crossref","unstructured":"Wieting, J., Bansal, M., Gimpel, K., Livescu, K.: Charagram: embedding words and sentences via character n-grams. In: Conference on Empirical Methods in Natural Language Processing (2016)","DOI":"10.18653\/v1\/D16-1157"},{"key":"1_CR97","unstructured":"Wu, Y., et al.: Google\u2019s neural machine translation system: Bridging the gap between human and machine translation. CoRR abs\/1609.08144 (2016)"},{"key":"1_CR98","unstructured":"Xiao, Y., Cho, K.: Efficient character-level document classification by combining convolution and recurrent layers. CoRR abs\/1602.00367 (2016)"},{"key":"1_CR99","doi-asserted-by":"crossref","unstructured":"Yaghoobzadeh, Y., Sch\u00fctze, H.: Multi-level representations for fine-grained typing of knowledge base entities. In: Conference of the European Chapter of the Association for Computational Linguistics (2017)","DOI":"10.18653\/v1\/E17-1055"},{"key":"1_CR100","unstructured":"Yang, Z., Chen, W., Wang, F., Xu, B.: A character-aware encoder for neural machine translation. In: International Conference on Computational Linguistics, pp. 3063\u20133070 (2016)"},{"key":"1_CR101","unstructured":"Yang, Z., Salakhutdinov, R., Cohen, W.W.: Multi-task cross-lingual sequence tagging from scratch. CoRR abs\/1603.06270 (2016)"},{"key":"1_CR102","doi-asserted-by":"crossref","unstructured":"Yu, L., Buys, J., Blunsom, P.: Online segment to segment neural transduction. In: Conference on Empirical Methods in Natural Language Processing, pp. 1307\u20131316 (2016)","DOI":"10.18653\/v1\/D16-1138"},{"key":"1_CR103","unstructured":"Zhang, X., LeCun, Y.: Text understanding from scratch. CoRR abs\/1502.01710 (2015)"},{"key":"1_CR104","unstructured":"Zhang, X., Zhao, J., LeCun, Y.: Character-level convolutional networks for text classification. In: Advances in Neural Information Processing Systems, pp. 649\u2013657 (2015)"}],"container-title":["Lecture Notes in Computer Science","Computational Linguistics and Intelligent Text Processing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-77113-7_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T19:07:14Z","timestamp":1775243234000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-77113-7_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319771120","9783319771137"],"references-count":104,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-77113-7_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"CICLing","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Linguistics and Intelligent Text Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Budapest","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hungary","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2017","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 April 2017","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 April 2017","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cicling2017","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.cicling.org\/2017\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}