{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T17:51:52Z","timestamp":1776275512117,"version":"3.50.1"},"reference-count":62,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,2,2]],"date-time":"2022-02-02T00:00:00Z","timestamp":1643760000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,2,2]],"date-time":"2022-02-02T00:00:00Z","timestamp":1643760000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100023704","name":"CLARIN ERIC","doi-asserted-by":"crossref","award":["ParlaMint: Towards Comparable Parliamentary Corpora (2020-2021"],"award-info":[{"award-number":["ParlaMint: Towards Comparable Parliamentary Corpora (2020-2021"]}],"id":[{"id":"10.13039\/501100023704","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100023704","name":"CLARIN ERIC","doi-asserted-by":"crossref","award":["ParlaFormat (2019)"],"award-info":[{"award-number":["ParlaFormat (2019)"]}],"id":[{"id":"10.13039\/501100023704","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Lang Resources &amp; Evaluation"],"published-print":{"date-parts":[[2023,3]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>This paper presents the ParlaMint corpora containing transcriptions of the sessions of the 17 European national parliaments with half a billion words. The corpora are uniformly encoded, contain rich meta-data about 11 thousand speakers, and are linguistically annotated following the Universal Dependencies formalism and with named entities. Samples of the corpora and conversion scripts are available from the project\u2019s GitHub repository, and the complete corpora are openly available via the CLARIN.SI repository for download, as well as through the NoSketch Engine and KonText concordancers and the Parlameter interface for on-line exploration and analysis.<\/jats:p>","DOI":"10.1007\/s10579-021-09574-0","type":"journal-article","created":{"date-parts":[[2022,2,2]],"date-time":"2022-02-02T05:02:29Z","timestamp":1643778149000},"page":"415-448","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":49,"title":["The ParlaMint corpora of parliamentary proceedings"],"prefix":"10.1007","volume":"57","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1560-4099","authenticated-orcid":false,"given":"Toma\u017e","family":"Erjavec","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3467-9424","authenticated-orcid":false,"given":"Maciej","family":"Ogrodniczuk","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4484-5027","authenticated-orcid":false,"given":"Petya","family":"Osenova","sequence":"additional","affiliation":[]},{"given":"Nikola","family":"Ljube\u0161i\u0107","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3555-0179","authenticated-orcid":false,"given":"Kiril","family":"Simov","sequence":"additional","affiliation":[]},{"given":"Andrej","family":"Pan\u010dur","sequence":"additional","affiliation":[]},{"given":"Micha\u0142","family":"Rudolf","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7953-8783","authenticated-orcid":false,"given":"Maty\u00e1\u0161","family":"Kopp","sequence":"additional","affiliation":[]},{"given":"Starka\u00f0ur","family":"Barkarson","sequence":"additional","affiliation":[]},{"given":"Stein\u00fe\u00f3r","family":"Steingr\u00edmsson","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1031-6327","authenticated-orcid":false,"given":"\u00c7a\u011fr\u0131","family":"\u00c7\u00f6ltekin","sequence":"additional","affiliation":[]},{"given":"Jesse","family":"de Does","sequence":"additional","affiliation":[]},{"given":"Katrien","family":"Depuydt","sequence":"additional","affiliation":[]},{"given":"Tommaso","family":"Agnoloni","sequence":"additional","affiliation":[]},{"given":"Giulia","family":"Venturi","sequence":"additional","affiliation":[]},{"given":"Mar\u00eda Calzada","family":"P\u00e9rez","sequence":"additional","affiliation":[]},{"given":"Luciana D.","family":"de Macedo","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4242-9249","authenticated-orcid":false,"given":"Costanza","family":"Navarretta","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2766-0175","authenticated-orcid":false,"given":"Giancarlo","family":"Luxardo","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9279-931X","authenticated-orcid":false,"given":"Matthew","family":"Coole","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1257-2191","authenticated-orcid":false,"given":"Paul","family":"Rayson","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2174-0396","authenticated-orcid":false,"given":"Vaidas","family":"Morkevi\u010dius","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8509-420X","authenticated-orcid":false,"given":"Tomas","family":"Krilavi\u010dius","sequence":"additional","affiliation":[]},{"given":"Roberts","family":"Dar\u01f5is","sequence":"additional","affiliation":[]},{"given":"Orsolya","family":"Ring","sequence":"additional","affiliation":[]},{"given":"Ruben","family":"van Heusden","sequence":"additional","affiliation":[]},{"given":"Maarten","family":"Marx","sequence":"additional","affiliation":[]},{"given":"Darja","family":"Fi\u0161er","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,2,2]]},"reference":[{"key":"9574_CR2","first-page":"1","volume-title":"Cross-cultural perspectives on parliamentary discourse","author":"P Bayley","year":"2014","unstructured":"Bayley, P. (2014). Introduction: The whys and wherefores of analyzing parliamentary discourse. In P. Bayley (Ed.), Cross-cultural perspectives on parliamentary discourse (pp. 1\u201344). John Benjamins Publishing."},{"key":"9574_CR3","unstructured":"Calabretta, I., Dalton, C., Griscom, R., Ko\u0142czy\u0144ska, M., Pahor\u00a0de Maiti, K., & Ros, R. (2021). Parliamentary debates in the COVID times. Retrieved from https:\/\/dhhackathon.wordpress.com\/2021\/05\/28\/parliamentary-debates-in-the-covid-times\/"},{"key":"9574_CR4","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1075\/tis.12.2.03cal","volume":"12","author":"M Calzada Perez","year":"2017","unstructured":"Calzada Perez, M. (2017). Corpus-based methods for comparative translation and interpreting studies: Mapping differences and similarities with traditional and innovative tools. Translation and Interpreting Studies, 12, 231\u2013252. https:\/\/doi.org\/10.1075\/tis.12.2.03cal.","journal-title":"Translation and Interpreting Studies"},{"issue":"5","key":"9574_CR5","doi-asserted-by":"publisher","first-page":"562","DOI":"10.1177\/0957926515581157","volume":"26","author":"JE Cheng","year":"2015","unstructured":"Cheng, J. E. (2015). Islamophobia, Muslimophobia or racism? Parliamentary discourses on Islam and Muslims in debates on the minaret ban in Switzerland. Discourse & Society, 26(5), 562\u2013586.","journal-title":"Discourse & Society"},{"key":"9574_CR6","unstructured":"\u00c7\u00f6ltekin, \u00c7. (2010). A freely available morphological analyzer for Turkish. In Proceedings of the 7th International Conference on Language Resources and Evaluation (LREC) (pp. 820\u2013827). Retrieved from http:\/\/www.lrec-conf.org\/proceedings\/lrec2010\/summaries\/109.html"},{"key":"9574_CR7","unstructured":"\u00c7\u00f6ltekin, \u00c7. (2014). A set of open source tools for turkish natural language processing. In N.\u00a0Calzolari, K.\u00a0Choukri, T.\u00a0Declerck, H.\u00a0Loftsson, B.\u00a0Maegaard, J.\u00a0Mariani, A.\u00a0Moreno, J.\u00a0Odijk, S.\u00a0Piperidis (Eds.), Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC\u201914) (pp. 1079\u20131086). European Language Resources Association (ELRA). http:\/\/www.lrec-conf.org\/proceedings\/lrec2014\/pdf\/437_Paper.pdf"},{"issue":"2","key":"9574_CR35","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1162\/coli_a_00402","volume":"47","author":"MC de Marneffe","year":"2021","unstructured":"de Marneffe, M. C., Manning, C. D., Nivre, J., & Zeman, D. (2021). Universal dependencies. Computational Linguistics, 47(2), 255\u2013308. https:\/\/doi.org\/10.1162\/coli_a_00402.","journal-title":"Computational Linguistics"},{"key":"9574_CR8","unstructured":"Dell\u2019Orletta, F., Venturi, G., Cimino, A., & Montemagni, S. (2014). T2K2: A system for automatically extracting and organizing knowledge from texts. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC\u201914), pp. 2062\u20132070. European Language Resources Association (ELRA). Retrieved from  http:\/\/www.lrec-conf.org\/proceedings\/lrec2014\/pdf\/590_Paper.pdf"},{"key":"9574_CR10","unstructured":"Diwersy, S., & Luxardo, G. (2020). Querying a large annotated corpus of parliamentary debates. In Proceedings of the Second ParlaCLARIN Workshop (pp. 75\u201379). European Language Resources Association (ELRA). Retrieved from https:\/\/www.aclweb.org\/anthology\/2020.parlaclarin-1.13"},{"key":"9574_CR11","unstructured":"Erjavec, T., Ogrodniczuk, M., Osenova, P., Ljube\u0161i\u0107, N., Simov, K., Grigorova, V., Rudolf, M., Pan\u010dur, A., Kopp, M., Barkarson, S., Steingr\u00edmsson, S., van\u00a0der Pol, H., Depoorter, G., de\u00a0Does, J., Jongejan, B., Haltrup\u00a0Hansen, D., Navarretta, C., Calzada\u00a0P\u00e9rez, M., de\u00a0Macedo, L. D., \u2026, Rayson, P. (2021a). Multilingual comparablecorpora of parliamentary debates ParlaMint 2.1. Slovenian language resource repository CLARIN.SI. Retrieved from http:\/\/hdl.handle.net\/11356\/1432"},{"key":"9574_CR12","unstructured":"Erjavec, T., Ogrodniczuk, M., Osenova, P., Ljube\u0161i\u0107, N., Simov, K., Grigorova, V., Rudolf, M., Pan\u010dur, A., Kopp, M., Barkarson, S., Steingr\u00edmsson, S., van\u00a0der Pol, H., Depoorter, G., de\u00a0Does, J., Jongejan, B., Haltrup\u00a0Hansen, D., Navarretta, C., Calzada\u00a0P\u00e9rez, M., de\u00a0Macedo, L. D., \u2026, Rayson, P. (2021b). Linguisticallyannotated multilingual comparable corpora of parliamentary debates ParlaMint.ana 2.1. Slovenian language resource repository CLARIN.SI. Retrieved from http:\/\/hdl.handle.net\/11356\/1431"},{"key":"9574_CR13","doi-asserted-by":"publisher","unstructured":"Erjavec, T., & Pan\u010dur, A. (2019). Parla-CLARIN: TEI guidelines for corpora of parliamentary proceedings. https:\/\/doi.org\/10.5281\/zenodo.3446164.","DOI":"10.5281\/zenodo.3446164"},{"key":"9574_CR14","unstructured":"Evert, S., & Hardie, A. (2011). Twenty-first century Corpus Workbench: Updating a query architecture for the new millennium. In Proceedings of the Corpus Linguistics 2011 conference. University of Birmingham. Retrieved from https:\/\/www.birmingham.ac.uk\/documents\/college-artslaw\/corpus\/conference-archives\/2011\/Paper-153.pdf"},{"key":"9574_CR15","unstructured":"Fi\u0161er, D., Eskevich, M., de\u00a0Jong, F. (Eds.). (2020). Proceedings of the Second ParlaCLARIN Workshop. European Language Resources Association (ELRA). https:\/\/www.aclweb.org\/anthology\/2020.parlaclarin-1.0"},{"key":"9574_CR16","unstructured":"Fi\u0161er, D., Lenardi\u010d, J., & Erjavec, T. (2018). CLARIN\u2019s Key Resource Families. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018). European Language Resources Association (ELRA). Retrieved from https:\/\/www.aclweb.org\/anthology\/L18-1210"},{"key":"9574_CR17","unstructured":"Fi\u0161er, D., Eskevich, M., & de\u00a0Jong, F. (Eds.). (2018). Proceedings of LREC 2018 Workshop ParlaCLARIN: Creating and Using Parliamentary Corpora. European Language Resources Association (ELRA). Retrieved from http:\/\/lrec-conf.org\/workshops\/lrec2018\/W2\/pdf\/book_of_proceedings.pdf"},{"key":"9574_CR18","unstructured":"Fi\u0161er, D., & Lenardi\u010d, J. (2018). CLARIN Corpora for Parliamentary Discourse Research. In Proceedings of the LREC2018 Workshop ParlaCLARIN: Creating and Using Parliamentary Corpora. European Language Resources Association. Retrieved from http:\/\/lrec-conf.org\/workshops\/lrec2018\/W2\/summaries\/14_W2.html"},{"key":"9574_CR19","doi-asserted-by":"crossref","unstructured":"Fi\u0161er, D., & Pahor De Maiti, K. (2020). Voices of the parliament. Modern Languages Open 1, 1\u201323.","DOI":"10.3828\/mlo.v0i0.295"},{"key":"9574_CR20","doi-asserted-by":"publisher","unstructured":"Fi\u0161er, D., & Pahor De\u00a0Maiti, K. (2021). \u201cFirst, I\u2019m a Female Politician, Not a Male One, and Second...\u201d: A corpus approach to parliamentary discourse research. Contributions of contemporary history 61(1), 144\u2013179. https:\/\/doi.org\/10.51663\/pnz.61.1.07","DOI":"10.51663\/pnz.61.1.07"},{"key":"9574_CR21","unstructured":"Hirst, G., Wei\u00a0Feng, V., Cochrane, C., & Naderi, N. (2014). Argumentation, ideology, and issue framing in parliamentary discourse. In ArgNLP. ftp:\/\/www.cs.toronto.edu\/pub\/gh\/Hirst-etal-Bertinoro-2014.pdf"},{"key":"9574_CR22","unstructured":"Hladk\u00e1, B., Kopp, M., & Stra\u0148\u00e1k, P. (2020). ParCzech PS7 1.0. http:\/\/hdl.handle.net\/11234\/1-3174. LINDAT\/CLARIAH-CZ digital library at the Institute of Formal and Applied Linguistics (\u00daFAL), Faculty of Mathematics and Physics, Charles University"},{"key":"9574_CR23","unstructured":"Hladk\u00e1, B., Kopp, M., & Stra\u0148\u00e1k, P. (2020). Compiling Czech parliamentary stenographic protocols into a corpus. In Proceedings of the LREC 2020 Workshop on Creating, Using and Linking of Parliamentary Corpora with Other Types of Political Discourse (ParlaCLARIN II) (pp. 18\u201322). European Language Resources Association (ELRA)"},{"issue":"2","key":"9574_CR24","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1093\/llc\/fqt054","volume":"30","author":"LM Hughes","year":"2013","unstructured":"Hughes, L. M., Ell, P. S., Knight, G. A. G., & Dobreva, M. (2013). Assessing and measuring impact of a digital collection in the humanities: An analysis of the SPHERE (Stormont Parliamentary Hansards: Embedded in Research and Education) Project. Digital Scholarship in the Humanities, 30(2), 183\u2013198.","journal-title":"Digital Scholarship in the Humanities"},{"key":"9574_CR25","unstructured":"Ing\u00f3lfsd\u00f3ttir, S. L., Loftsson, H., Dadason, J. F., & Bjarnad\u00f3ttir, K. (2019). Nefnir: A high accuracy lemmatizer for Icelandic. In Proceedings of the 22nd Nordic Conference on Computational Linguistics, NODALIDA."},{"key":"9574_CR26","unstructured":"Jongejan, B., Hansen, D. H., & Navarretta, C. (2021). Enhancing CLARIN-DK resources while building the Danish ParlaMint corpus. In CLARIN Annual Conference 2021 Proceedings, pp. 70\u201373. CLARIN ERIC. Retrieved from https:\/\/office.clarin.eu\/v\/CE-2021-1923-CLARIN2021_ConferenceProceedings.pdf"},{"issue":"1","key":"9574_CR27","first-page":"75","volume":"I","author":"W Kiera\u015b","year":"2017","unstructured":"Kiera\u015b, W., & Woli\u0144ski, M. (2017). Morfeusz 2: Analizator i generator fleksyjny dla jezyka polskiego. Jezyk Polski XCVI, I(1), 75\u201383.","journal-title":"Jezyk Polski XCVI"},{"key":"9574_CR28","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1007\/s40607-014-0009-9","volume":"1","author":"A Kilgarriff","year":"2014","unstructured":"Kilgarriff, A., Baisa, V., Bu\u0161ta, J., Jakub\u00ed\u010dek, M., Kov\u00e1\u0159, V., Michelfeit, J., et al. (2014). The Sketch Engine: Ten years on. Lexicography, 1, 7\u201336.","journal-title":"Lexicography"},{"key":"9574_CR29","doi-asserted-by":"crossref","unstructured":"Klein, G., Kim, Y., Deng, Y., Senellart, J., & Rush, A. (2017). OpenNMT: Open-source toolkit for neural machine translation. In Proceedings of ACL 2017, System Demonstrations (pp. 67\u201372). Association for Computational Linguistics. Retrieved from https:\/\/www.aclweb.org\/anthology\/P17-4012","DOI":"10.18653\/v1\/P17-4012"},{"key":"9574_CR30","unstructured":"Kopp, M., Stankov, V., Bojar, O., Hladk\u00e1, B., & Stra\u0148\u00e1k, P. (2021). ParCzech 3.0. http:\/\/hdl.handle.net\/11234\/1-3631. LINDAT\/CLARIAH-CZ digital library at the Institute of Formal and Applied Linguistics (\u00daFAL). Faculty of Mathematics and Physics, Charles University"},{"key":"9574_CR31","doi-asserted-by":"publisher","unstructured":"Kopp, M., Stankov, V., Kr\u016fza, J., Stra\u0148\u00e1k, P., & Bojar, O. (2021). ParCzech 3.0: A large Czech speech corpus with rich metadata. In K.\u00a0Ek\u0161tein, F.\u00a0P\u00e1rtl, & M.\u00a0Konop\u00edk (Eds.), Text, Speech, and Dialogue, Lecture Notes in Computer Science (pp. 293\u2013304). University of West Bohemia, Springer. https:\/\/doi.org\/10.1007\/978-3-030-83527-9_25.","DOI":"10.1007\/978-3-030-83527-9_25"},{"key":"9574_CR32","doi-asserted-by":"publisher","unstructured":"Ljube\u0161i\u0107, N., & Dobrovoljc, K. (2019). What does Neural Bring? Analysing improvements in morphosyntactic annotation and lemmatisation of Slovenian, Croatian and Serbian. In Proceedings of the 7th Workshop on Balto-Slavic Natural Language Processing (pp. 29\u201334). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/W19-3704. https:\/\/www.aclweb.org\/anthology\/W19-3704","DOI":"10.18653\/v1\/W19-3704"},{"key":"9574_CR33","unstructured":"Mach\u00e1lek, T. (2020). KonText: Advanced and Flexible Corpus Query Interface. In Proceedings of the 12th language resources and evaluation conference (pp. 7003\u20137008). European Language Resources Association. Retrieved from https:\/\/www.aclweb.org\/anthology\/2020.lrec-1.865"},{"key":"9574_CR34","first-page":"231","volume-title":"Intelligent tools for building a scientific information platform, studies in computational intelligence","author":"M Marci\u0144czuk","year":"2013","unstructured":"Marci\u0144czuk, M., Koco\u0144, J., & Janicki, M. (2013). Liner2: A customizable framework for proper names recognition for Polish. In R. Bembenik, \u0141 Skonieczny, H. Rybi\u0144ski, M. Kryszkiewicz, & M. Niezg\u00f3dka (Eds.), Intelligent tools for building a scientific information platform, studies in computational intelligence (Vol. 467, pp. 231\u2013253). Springer-Verlag."},{"key":"9574_CR36","unstructured":"Neuhold, C. (2020). European Parliaments in Times of Coronavirus. Retrieved from https:\/\/www.e-ir.info\/2020\/04\/18\/european-parliaments-in-times-of-coronavirus\/"},{"key":"9574_CR37","doi-asserted-by":"crossref","unstructured":"Nguyen, M. V., Lai, V., Veyseh, A. P. B., & Nguyen, T. H. (2021). Trankit: A light-weight transformer-based toolkit for multilingual natural language processing. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations.","DOI":"10.18653\/v1\/2021.eacl-demos.10"},{"key":"9574_CR38","unstructured":"Ogrodniczuk, M. (2012). The Polish Sejm Corpus. In N. Calzolari, K. Choukri, T. Declerck, M.U. Do\u011fan, B. Maegaard, J. Mariani, J. Odijk, S. Piperidis (Eds.), Proceedings of the 8th International Conference on Language Resources and Evaluation (LREC 2012) (pp. 2219\u20132223). European Language Resource Association."},{"key":"9574_CR39","unstructured":"Ogrodniczuk, M. (2018). Polish Parliamentary Corpus. In Proceedings of the LREC2018 Workshop ParlaCLARIN: Creating and Using Parliamentary Corpora. European Language Resources Association. Retrieved from http:\/\/lrec-conf.org\/workshops\/lrec2018\/W2\/summaries\/11_W2.html"},{"key":"9574_CR40","unstructured":"Ogrodniczuk, M., & Nito\u0144, B. (2020). New developments in the Polish Parliamentary Corpus. In Proceedings of the Second ParlaCLARIN Workshop, pp. 1\u20134. European Language Resources Association (ELRA). Retrieved from https:\/\/www.aclweb.org\/anthology\/2020.parlaclarin-1.1"},{"key":"9574_CR41","unstructured":"Osenova, P., & Simov, K. (2012). The Political Speech Corpus of Bulgarian. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC\u201912) (pp. 1744\u20131747). European Language Resources Association (ELRA). Retrieved from http:\/\/www.lrec-conf.org\/proceedings\/lrec2012\/pdf\/956_Paper.pdf"},{"key":"9574_CR42","unstructured":"Pan\u010dur, A., & Erjavec, T. (2020). The siParl corpus of Slovenian parliamentary proceedings. In ParlaCLARIN II: LREC2020 workshop on creating, using and linking parliamentary corpora with other types of political discourse. Retrieved from https:\/\/www.aclweb.org\/anthology\/2020.parlaclarin-1.6"},{"key":"9574_CR43","unstructured":"Pan\u010dur, A., Erjavec, T., Ojster\u0161ek, M., \u0160orn, M., & Blaj\u00a0Hribar, N. (2019). Slovenian parliamentary corpus (1990\u20132018) siParl 1.0. Retrieved from http:\/\/hdl.handle.net\/11356\/1236"},{"key":"9574_CR44","unstructured":"Pan\u010dur, A., Erjavec, T., Ojster\u0161ek, M., \u0160orn, M., & Blaj\u00a0Hribar, N. (2020). Slovenian parliamentary corpus (1990\u20132018) siParl 2.0. Retrieved from http:\/\/hdl.handle.net\/11356\/1300"},{"key":"9574_CR45","doi-asserted-by":"crossref","unstructured":"Pan\u010dur, A., & \u0160orn, M. (2016). Smart Big Data: Use of Slovenian Parliamentary Papers in Digital History. Prispevki za novej\u0161o zgodovino 56(3), 130\u2013146. https:\/\/ojs.inz.si\/pnz\/article\/view\/193","DOI":"10.51663\/pnz.56.3.09"},{"key":"9574_CR46","unstructured":"Przepi\u00f3rkowski, A., Ba\u0144ko, M., G\u00f3rski, R. L., & Lewandowska-Tomaszczyk, B. (Eds.). (2012). Narodowy Korpus Jezyka Polskiego [EN: National Corpus of Polish]. Warsaw: PWN Scientific Publishers."},{"key":"9574_CR47","doi-asserted-by":"crossref","unstructured":"Qi, P., Dozat, T., Zhang, Y., & Manning, C. D. (2019). Universal dependency parsing from scratch. In Proceedings of the CoNLL 2018 Shared Task: Multilingual parsing from raw text to universal dependencies (pp. 160\u2013170). Retrieved from https:\/\/nlp.stanford.edu\/pubs\/qi2018universal.pdf","DOI":"10.18653\/v1\/K18-2016"},{"key":"9574_CR48","doi-asserted-by":"publisher","unstructured":"Qi, P., Zhang, Y., Zhang, Y., Bolton, J., & Manning, C.D. (2020). Stanza: A Python natural language processing toolkit for many human languages. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations (pp. 101\u2013108). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2020.acl-demos.14. https:\/\/aclanthology.org\/2020.acl-demos.14","DOI":"10.18653\/v1\/2020.acl-demos.14"},{"issue":"12","key":"9574_CR49","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pone.0168843","volume":"11","author":"L Rheault","year":"2016","unstructured":"Rheault, L., Beelen, K., Cochrane, C., & Hirst, G. (2016). Measuring emotion in parliamentary debates with automated textual analysis. PLoS ONE, 11(12), 1\u201318. https:\/\/doi.org\/10.1371\/journal.pone.0168843.","journal-title":"PLoS ONE"},{"key":"9574_CR50","doi-asserted-by":"crossref","unstructured":"Rybak, P., & Wr\u00f3blewska, A. (2018). Semi-supervised neural system for tagging, parsing and lematization. In Proceedings of the CoNLL 2018 Shared Task: Multilingual parsing from raw text to universal dependencies (pp. 45\u201354). Association for Computational Linguistics. Retrieved from http:\/\/www.aclweb.org\/anthology\/K18-2004","DOI":"10.18653\/v1\/K18-2004"},{"key":"9574_CR51","unstructured":"Rychl\u00fd, P. (2007). Manatee\/Bonito: A modular corpus manager. In 1st Workshop on Recent Advances in Slavonic Natural Language Processing (pp. 65\u201370). Masarykova univerzita."},{"key":"9574_CR52","unstructured":"Steingr\u00edmsson, S., Barkarson, S., & \u00d6rn\u00f3lfsson, G.T. (2020). IGC-Parl: Icelandic Corpus of Parliamentary Proceedings. In Proceedings of the Second ParlaCLARIN Workshop (pp. 11\u201317). European Language Resources Association. Retrieved from https:\/\/www.aclweb.org\/anthology\/2020.parlaclarin-1.3"},{"key":"9574_CR53","unstructured":"Steingr\u00edmsson, S., Helgad\u00f3ttir, S., R\u00f6gnvaldsson, E., Barkarson, S., & Gu\u00f0nason, J. (2018). Risam\u00e1lheild: A very large Icelandic text corpus. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)."},{"key":"9574_CR54","doi-asserted-by":"crossref","unstructured":"Steingr\u00edmsson, S., K\u00e1rason, \u00d6., & Loftsson, H. (2019). Augmenting a BiLSTM tagger with a morphological lexicon and a lexical category identification step. In Proceedings of RANLP.","DOI":"10.26615\/978-954-452-056-4_133"},{"key":"9574_CR55","doi-asserted-by":"publisher","unstructured":"Straka, M. (2018). UDPipe 2.0 Prototype at CoNLL 2018 UD shared task. In Proceedings of the CoNLL 2018 ST: Multilingual parsing from raw text to universal dependencies (pp. 197\u2013207). Association for Computational Linguistics. Retrieved from https:\/\/doi.org\/10.18653\/v1\/K18-2020","DOI":"10.18653\/v1\/K18-2020"},{"key":"9574_CR56","doi-asserted-by":"crossref","unstructured":"Straka, M., & Strakov\u00e1, J. (2017). Tokenizing, POS tagging, lemmatizing and parsing UD 2.0 with UDPipe. In Proceedings of the CoNLL 2017 shared task: Multilingual Parsing from raw text to universal dependencies (pp. 88\u201399). Association for Computational Linguistics. Retrieved from http:\/\/www.aclweb.org\/anthology\/K\/K17\/K17-3009.pdf","DOI":"10.18653\/v1\/K17-3009"},{"key":"9574_CR57","doi-asserted-by":"crossref","unstructured":"Strakov\u00e1, J., Straka, M., & Haji\u010d, J. (2019). Neural architectures for nested NER through linearization. In Proceedings of the 57th Annual meeting of the association for computational linguistics (pp. 5326\u20135331). Association for Computational Linguistics","DOI":"10.18653\/v1\/P19-1527"},{"key":"9574_CR58","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-024-0881-2_31","volume-title":"Czech Named Entity Corpus","author":"J Strakov\u00e1","year":"2017","unstructured":"Strakov\u00e1, J., Straka, M., \u0160ev\u010d\u00edkov\u00e1, M., & \u017dabokrtsk\u00fd, Z. (2017). Czech named entity corpus. Springer."},{"key":"9574_CR59","unstructured":"TEI\u00a0Consortium (Ed.). (2017). TEI P5: Guidelines for electronic text encoding and interchange. TEI Consortium. Retrieved from http:\/\/www.tei-c.org\/Guidelines\/P5\/"},{"key":"9574_CR60","doi-asserted-by":"crossref","unstructured":"Truan, N., & Romary, L. (2020). Building, encoding, and annotating a corpus of parliamentary debates in XML-TEI: A cross-linguistic account. Retrieved from https:\/\/halshs.archives-ouvertes.fr\/halshs-03097333.","DOI":"10.4000\/jtei.4164"},{"issue":"2","key":"9574_CR1","doi-asserted-by":"publisher","first-page":"271","DOI":"10.3233\/SW-160227","volume":"8","author":"A van Aggelen","year":"2017","unstructured":"van Aggelen, A., Hollink, L., Kemman, M., Kleppe, M., & Beunders, H. (2017). The debates of the European Parliament as linked open data. Semantic Web, 8(2), 271\u2013281. https:\/\/doi.org\/10.3233\/SW-160227.","journal-title":"Semantic Web"},{"key":"9574_CR9","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1075\/dapsac.38.03dij","volume-title":"European parliaments under scrutiny: Discourse strategies and interaction practices","author":"TA van Dijk","year":"2010","unstructured":"van Dijk, T. A. (2010). Political identities in parliamentary debates. In C. Ili (Ed.), European parliaments under scrutiny: Discourse strategies and interaction practices (pp. 29\u201356). John Benjamins Publishing."},{"key":"9574_CR61","doi-asserted-by":"crossref","unstructured":"Waszczuk, J., Kiera\u015b, W., & Woli\u0144ski, M. (2018). Morphosyntactic disambiguation and segmentation for historical Polish with graph-based conditional random fields. In P.\u00a0Sojka, A.\u00a0Hor\u00e1k, I.\u00a0Kope\u010dek, K.\u00a0Pala (Eds.), Text, Speech, and Dialogue: 21st International Conference, TSD\u00a02018. Proceedings, no. 11107 in Lecture Notes in Artificial Intelligence, September 11\u201314 (pp. 188\u2013196). Springer-Verlag","DOI":"10.1007\/978-3-030-00794-2_20"},{"key":"9574_CR62","doi-asserted-by":"publisher","unstructured":"Znoti\u0146\u0161, A., & Clrule, E. (2018). NLP-PIPE: Latvian NLP tool pipeline. IOS Press. https:\/\/doi.org\/10.3233\/978-1-61499-912-6-183","DOI":"10.3233\/978-1-61499-912-6-183"}],"container-title":["Language Resources and Evaluation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10579-021-09574-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10579-021-09574-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10579-021-09574-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,27]],"date-time":"2023-03-27T01:27:48Z","timestamp":1679880468000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10579-021-09574-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,2]]},"references-count":62,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,3]]}},"alternative-id":["9574"],"URL":"https:\/\/doi.org\/10.1007\/s10579-021-09574-0","relation":{},"ISSN":["1574-020X","1574-0218"],"issn-type":[{"value":"1574-020X","type":"print"},{"value":"1574-0218","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2,2]]},"assertion":[{"value":"20 December 2021","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 February 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}