{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T01:17:58Z","timestamp":1773883078288,"version":"3.50.1"},"reference-count":41,"publisher":"Cambridge University Press (CUP)","issue":"5","license":[{"start":{"date-parts":[[2020,5,27]],"date-time":"2020-05-27T00:00:00Z","timestamp":1590537600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["cambridge.org"],"crossmark-restriction":true},"short-container-title":["Nat. Lang. Eng."],"published-print":{"date-parts":[[2021,9]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>In this paper, we present a novel lemmatization method based on a sequence-to-sequence neural network architecture and morphosyntactic context representation. In the proposed method, our context-sensitive lemmatizer generates the lemma one character at a time based on the surface form characters and its morphosyntactic features obtained from a morphological tagger. We argue that a sliding window context representation suffers from sparseness, while in majority of cases the morphosyntactic features of a word bring enough information to resolve lemma ambiguities while keeping the context representation dense and more practical for machine learning systems. Additionally, we study two different data augmentation methods utilizing autoencoder training and morphological transducers especially beneficial for low-resource languages. We evaluate our lemmatizer on 52 different languages and 76 different treebanks, showing that our system outperforms all latest baseline systems. Compared to the best overall baseline, UDPipe Future, our system outperforms it on 62 out of 76 treebanks reducing errors on average by 19% relative. The lemmatizer together with all trained models is made available as a part of the Turku-neural-parsing-pipeline under the Apache 2.0 license.<\/jats:p>","DOI":"10.1017\/s1351324920000224","type":"journal-article","created":{"date-parts":[[2020,5,27]],"date-time":"2020-05-27T08:02:48Z","timestamp":1590566568000},"page":"545-574","update-policy":"https:\/\/doi.org\/10.1017\/policypage","source":"Crossref","is-referenced-by-count":18,"title":["Universal Lemmatizer: A sequence-to-sequence model for lemmatizing Universal Dependencies treebanks"],"prefix":"10.1017","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4580-5366","authenticated-orcid":false,"given":"Jenna","family":"Kanerva","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Filip","family":"Ginter","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tapio","family":"Salakoski","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"56","published-online":{"date-parts":[[2020,5,27]]},"reference":[{"key":"S1351324920000224_ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"S1351324920000224_ref17","unstructured":"Kirov, C. , Sylak-Glassman, J. , Que, R. and Yarowsky, D. (2016). Very-large scale parsing and normalization of Wiktionary morphological paradigms. In Calzolari N. (Conference Chair), Choukri K., Declerck T., Goggi S., Grobelnik M., Maegaard B., Mariani J., Mazo H., Moreno A., Odijk J. and Piperidis S. (eds), Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016), Paris, France. European Language Resources Association (ELRA)."},{"key":"S1351324920000224_ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1126"},{"key":"S1351324920000224_ref16","unstructured":"Kingma, D. and Ba, J. (2015). Adam: a method for stochastic optimization. In Proceedings of the 3rd International Conference for Learning Representations."},{"key":"S1351324920000224_ref9","unstructured":"Dozat, T. and Manning, C.D. (2017). Deep biaffine attention for neural dependency parsing. In Proceedings of the 2017 International Conference on Learning Representations (ICLR\u201917)."},{"key":"S1351324920000224_ref28","first-page":"381","article-title":"Development and use of computational morphology of Finnish in the open source and open science era: notes on experiences with OMorFi development","volume":"28","author":"Pirinen","year":"2015","journal-title":"SKY Journal of Linguistics"},{"key":"S1351324920000224_ref15","volume-title":"Two-level rule compiler","author":"Karttunen","year":"1992"},{"key":"S1351324920000224_ref20","doi-asserted-by":"crossref","unstructured":"Koskenniemi, K. (1984). A general computational model for word-form recognition and production. In Proceedings of the 10th International Conference on Computational Linguistics, USA. Association for Computational Linguistics, pp. 178\u2013181.","DOI":"10.3115\/980431.980529"},{"key":"S1351324920000224_ref32","doi-asserted-by":"publisher","DOI":"10.3115\/1220575.1220635"},{"key":"S1351324920000224_ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"S1351324920000224_ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K17-3002"},{"key":"S1351324920000224_ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K17-2003"},{"key":"S1351324920000224_ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1136"},{"key":"S1351324920000224_ref22","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1002"},{"key":"S1351324920000224_ref26a","unstructured":"Nivre, J. , de Marneffe, M.-C. , Ginter, F. , Goldberg, Y. , Hajic, J. , Manning, C.D. , McDonald, R.T. , Petrov, S. , Pyysalo, S. , Silveira, N. , et al. (2016). Universal Dependencies v1: a multilingual treebank collection. In Proceedings of Language Resources and Evaluation Conference (LREC\u201916), Portoro\u017e, Slovenia. European Language Resources Association (ELRA)."},{"key":"S1351324920000224_ref1","doi-asserted-by":"publisher","DOI":"10.26615\/978-954-452-049-6_006"},{"key":"S1351324920000224_ref11","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1001"},{"key":"S1351324920000224_ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K17-2001"},{"key":"S1351324920000224_ref10a","unstructured":"Ginter, F. , Haji\u010d, J. , Luotolahti, J. , Straka, M. and Zeman, D. (2017). CoNLL 2017 Shared Task - automatically annotated raw texts and word embeddings. LINDAT\/CLARIN digital library at the Institute of Formal and Applied Linguistics (\u00daFAL), Faculty of Mathematics and Physics, Charles University."},{"key":"S1351324920000224_ref35","unstructured":"Straka, M. , Hajic, J. and Strakov\u00e1, J. (2016). UDPipe: trainable pipeline for processing CoNLL-U files performing tokenization, morphological analysis, pos tagging and parsing. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016), Portoro\u017e, Slovenia. European Language Resources Association (ELRA)."},{"key":"S1351324920000224_ref34","author":"Straka","year":"2018"},{"key":"S1351324920000224_ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-4009"},{"key":"S1351324920000224_ref12","unstructured":"Kanerva, J. , Ginter, F. , Miekka, N. , Leino, A. and Salakoski, T. (2018). Turku neural parser pipeline: an end-to-end system for the CoNLL 2018 Shared Task. In Proceedings of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, Brussels, Belgium. Association for Computational Linguistics."},{"key":"S1351324920000224_ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1532"},{"key":"S1351324920000224_ref37","doi-asserted-by":"publisher","DOI":"10.2478\/v10108-010-0015-5"},{"key":"S1351324920000224_ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6011"},{"key":"S1351324920000224_ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1272"},{"key":"S1351324920000224_ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-0309"},{"key":"S1351324920000224_ref39","volume-title":"Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies","author":"Zeman","year":"2017"},{"key":"S1351324920000224_ref36","first-page":"1670","volume-title":"Proceedings of 5th International Conference on Language Resources and Evaluation (LREC\u201906)","author":"Tr\u00f3n","year":"2006"},{"key":"S1351324920000224_ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-4111"},{"key":"S1351324920000224_ref38","first-page":"1","volume-title":"Proceedings of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies","author":"Zeman","year":"2018"},{"key":"S1351324920000224_ref27","doi-asserted-by":"crossref","unstructured":"\u00d6stling, R. and Bjerva, J. (2017). SU-RUG at the CoNLL-SIGMORPHON 2017 Shared Task: morphological inflection with attentional sequence-to-sequence models. In Proceedings of the CoNLL SIGMORPHON 2017 Shared Task: Universal Morphological Reinflection, Vancouver, Canada. Association for Computational Linguistics.","DOI":"10.18653\/v1\/K17-2012"},{"key":"S1351324920000224_ref6","unstructured":"\u00c7\u00f6ltekin, \u00c7. (2010). A freely available morphological analyzer for Turkish. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC\u201910), Valletta, Malta, vol. 2. European Language Resources Association (ELRA), pp. 19\u201328."},{"key":"S1351324920000224_ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-4012"},{"key":"S1351324920000224_ref26","unstructured":"Nivre, J. , Abrams, M. , Agi\u0107, \u017d. , Ahrenberg, L. , Antonsen, L. , Aranzabe, M.J. , Arutie, G. , Asahara, M. , Ateyah, L. , Attia, M. , Atutxa, A. , Augustinus, L. , Badmaeva, E. , Ballesteros, M. , Banerjee, E. , Bank, S. , Barbu Mititelu, V. , Bauer, J. , Bellato, S. , Bengoetxea, K. , Bhat, R.A. , Biagetti, E. , Bick, E. , Blokland, R. , Bobicev, V. , B\u00f6rstell, C. , Bosco, C. , Bouma, G. , Bowman, S. , Boyd, A. , Burchardt, A. , Candito, M. , Caron, B. , Caron, G. , Cebiro\u011flu Eryi\u011fit, G. , Celano, G.G.A. , Cetin, S. , Chalub, F. , Choi, J. , Cho, Y. , Chun, J. , Cinkov\u00e1, S. , Collomb, A. , \u00c7\u00f6ltekin, \u00c7. , Connor, M. , Courtin, M. , Davidson, E. , de Marneffe, M.-C. , de Paiva, V. , de Ilarraza, A.D. , Dickerson, C. , Dirix, P. , Dobrovoljc, K. , Dozat, T. , Droganova, K. , Dwivedi, P. , Eli, M. , Elkahky, A. , Ephrem, B. , Erjavec, T. , Etienne, A. , Farkas, R. , Fernandez Alcalde, H. , Foster, J. , Freitas, C. , Gajdo\u0161ov\u00e1, K. , Galbraith, D. , Garcia, M. , G\u00e4rdenfors, M. , Gerdes, K. , Ginter, F. , Goenaga, I. , Gojenola, K. , G\u00f6krmak, M. , Goldberg, Y. , G\u00f3mez Guinovart, X. , Gonz\u00e1les Saavedra, B. , Grioni, M. , Gr\u016bztis, N. , Guillaume, B. , Guillot-Barbance, C. , Habash, N. , Haji\u010d, J. , Haji\u010d, J. jr. , H\u00e0, M\u00f3 L. , Han, N.-R. , Harris, K. , Haug, D. , Hladk\u00e1, B. , Hlav\u00e1\u010dov\u00e1, J. , Hociung, F. , Hohle, P. , Hwang, J. , Ion, R. , Irimia, E. , Jelnek, T. , Johannsen, A. , J\u00f8rgensen, F. , Kaskara, H. , Kahane, S. , Kanayama, H. , Kanerva, J. , Kayadelen, T. , Kettnerov\u00e1, V. , Kirchner, J. , Kotsyba, N. , Krek, S. , Kwak, S. , Laippala, V. , Lambertino, L. , Lando, T. , Larasati, S.D. , Lavrentiev, A. , Lee, J. , L\u00ea H\u2019\u00f4ng, P. , Lenci, A. , Lertpradit, S. , Leung, H. , Li, C.Y. , Li, J. , Li, K. , Lim, K.T. , Ljube\u0161i\u0107, N. , Loginova, O. , Lyashevskaya, O. , Lynn, T. , Macketanz, V. , Makazhanov, A. , Mandl, M. , Manning, C. , Manurung, R. , M\u0103r\u0103nduc, C. , Mare\u010dek, D. , Marheinecke, K. , Martnez Alonso, H. , Martins, A. , Ma\u0161ek, J. , Matsumoto, Y. , McDonald, R. , Mendon\u00e7a, G. , Miekka, N. , Missil\u00e4, A. , Mititelu, C. , Miyao, Y. , Montemagni, S. , More, A. , Moreno Romero, L. , Mori, S. , Mortensen, B. , Moskalevskyi, B. , Muischnek, K. , Murawaki, Y. , M\u00fc\u00fcrisep, K. , Nainwani, P. , Navarro Hor\u00f1iacek, J.I. , Nedoluzhko, A. , Ne\u0161pore-B\u0113rzkalne, G. , Nguy\u00af\u00ean Thi, L. , Nguy\u00af\u00ean Thi Minh, H. , Nikolaev, V. , Nitisaroj, R. , Nurmi, H. , Ojala, S. , Ol\u00fa\u00f2kun, A. , Omura, M. , Osenova, P. , \u00d6stling, R. , \u00d8vrelid, L. , Partanen, N. , Pascual, E. , Passarotti, M. , Patejuk, A. , Peng, S. , Perez, C.-A. , Perrier, G. , Petrov, S. , Piitulainen, J. , Pitler, E. , Plank, B. , Poibeau, T. , Popel, M. , Pretkalnina, L. , Pr\u00e9vost, S. , Prokopidis, P. , Przepi\u00f3rkowski, A. , Puolakainen, T. , Pyysalo, S. , R\u00e4\u00e4bis, A. , Rademaker, A. , Ramasamy, L. , Rama, T. , Ramisch, C. , Ravishankar, V. , Real, L. , Reddy, S. , Rehm, G. , Rie\u00dfler, M. , Rinaldi, L. , Rituma, L. , Rocha, L. , Romanenko, M. , Rosa, R. , Rovati, D. , Rosca, V. , Rudina, O. , Sadde, S. , Saleh, S. , Samard\u017ei\u0107, T. , Samson, S. , Sanguinetti, M. , Saulte, B. , Sawanakunanon, Y. , Schneider, N. , Schuster, S. , Seddah, D. , Seeker, W. , Seraji, M. , Shen, M. , Shimada, A. , Shohibussirri, M. , Sichinava, D. , Silveira, N. , Simi, M. , Simionescu, R. , Simk\u00f3, K. , \u0160imkov\u00e1, M. , Simov, K. , Smith, A. , Soares-Bastos, I. , Stella, A. , Straka, M. , Strnadov\u00e1, J. , Suhr, A. , Sulubacak, U. , Sz\u00e1nt\u00f3, Z. , Taji, D. , Takahashi, Y. , Tanaka, T. , Tellier, I. , Trosterud, T. , Trukhina, A. , Tsarfaty, R. , Tyers, F. , Uematsu, S. , Ure\u0161ov\u00e1, Z. , Uria, L. , Uszkoreit, H. , Vajjala, S. , van Niekerk, D. , van Noord, G. , Varga, V. , Vincze, V. , Wallin, L. , Washington, J.N. , Williams, S. , Wir\u00e9n, M. , Woldemariam, T. , Wong, T.-s. , Yan, C. , Yavrumyan, M.M. , Yu, Z. , \u017dabokrtsk\u00fd, Z. , Zeldes, A. , Zeman, D. , Zhang, M. and Zhu, H. (2018). Universal Dependencies 2.2. LIN DAT\/CLARIN digital library at the Institute of Formal and Applied Linguistics (\u00daFAL), Faculty of Mathematics and Physics, Charles University."},{"key":"S1351324920000224_ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K17-2002"},{"key":"S1351324920000224_ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s12532-018-0144-7"},{"key":"S1351324920000224_ref5","unstructured":"Chrupa\u0142a, G. , Dinu, G. and Van Genabith, J. (2008). Learning morphology with Morfette. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC\u201908), Marrakech, Morocco. European Language Resources Association (ELRA), pp. 2362\u20132367."},{"key":"S1351324920000224_ref33","unstructured":"Straka, M. (2018a). CoNLL 2018 Shared Task - UDPipe baseline models and supplementary materials. LINDAT\/CLARIN digital library at the Institute of Formal and Applied Linguistics (\u00daFAL), Faculty of Mathematics and Physics, Charles University."},{"key":"S1351324920000224_ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K18-2016"}],"container-title":["Natural Language Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.cambridge.org\/core\/services\/aop-cambridge-core\/content\/view\/S1351324920000224","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T03:17:23Z","timestamp":1630466243000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.cambridge.org\/core\/product\/identifier\/S1351324920000224\/type\/journal_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5,27]]},"references-count":41,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2021,9]]}},"alternative-id":["S1351324920000224"],"URL":"https:\/\/doi.org\/10.1017\/s1351324920000224","relation":{},"ISSN":["1351-3249","1469-8110"],"issn-type":[{"value":"1351-3249","type":"print"},{"value":"1469-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,5,27]]},"assertion":[{"value":"\u00a9 The Author(s), 2020. Published by Cambridge University Press","name":"copyright","label":"Copyright","group":{"name":"copyright_and_licensing","label":"Copyright and Licensing"}},{"value":"This is an Open Access article, distributed under the terms of the Creative Commons Attribution licence (http:\/\/creativecommons.org\/licenses\/by\/4.0\/), which permits unrestricted re-use, distribution, and reproduction in any medium, provided the original work is properly cited.","name":"license","label":"License","group":{"name":"copyright_and_licensing","label":"Copyright and Licensing"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}