Detecting inflectional patterns for Croatian verb stems using class activation mappings

• Autorzy: Ševerdija Domagoj , Čorić Rebeka , Orešković Marko , Šošić Lucian

Identyfikatory

DOI

10.15398/jlm.v12i1.347

• Języki publikacji: EN

Abstrakty

EN

All verbal forms in the Croatian language can be derived from twobasic forms: the infinitive and the present stems. In this paper, wepresent a neural computation model that takes a verb in an infinitiveform and finds a mapping to a present form. The same model can beapplied vice-versa, i.e. map a verb from its present form to its infinitive form. Knowing the present form of a given verb, one can deduceits inflections using grammatical rules. We experiment with our modelon the Croatian language, which belongs to the Slavic group of lan-guages. The model learns a classifier through these two classification tasks and uses class activation mapping to find characters in verbs contributing to classification. The model detects patterns that follow established grammatical rules for deriving the present stem form from the infinitive stem form and vice-versa. If mappings can be found between such slots, the rest of the slots can be deduced using a rule-based system.

Słowa kluczowe

EN

Croatian infinitive and present verb stems; convolutional neural network; class activation mapping

• Wydawca: Instytut Podstaw Informatyki PAN
• Czasopismo: Journal of Language Modelling
• Rocznik: 2024
• Tom: Vol. 12, No. 1
• Strony: 43--68
• Opis fizyczny: Bibliogr. 26 poz., rys., tab.

Twórcy

autor

Ševerdija Domagoj

• Department of Mathematics, University J. J. Strossmayer of Osijek

• https://orcid.org/0000-0001-9501-1025

autor

Čorić Rebeka

• Department of Mathematics, University J. J. Strossmayer of Osijek

• https://orcid.org/0000-0002-2388-385X

autor

Orešković Marko

• National and University Library in Zagreb

• https://orcid.org/0000-0002-3723-9256

autor

Šošić Lucian

• Faculty of Humanities and Social Sciences in Split

• https://orcid.org/0000-0002-1523-493X

Bibliografia

• 1. P. J. ANTONY, Hemant B. RAJ, B. S. SAHANA, Dimple Sonal ALVARES, and Aishwarya RAJ (2012), Morphological analyzer and generator for Tululanguage: A novel approach, in Sabu M. THAMPI, El-Sayed EL-AFRY, and Javier AGUIAR, editors, Proceedings of the International Conference on Advances in Computing, Communications and Informatics, ICACCI ’12, pp. 828-834, Association for Computing Machinery, New York, NY, USA, doi:10.1145/2345396.2345531.z
• 2. Eugenija BARIĆ, Mijo LONČARIĆ, Dragica MALIĆ, Slavko PAVEŠIĆ, Mirko PETI, Vesna ZEČEVIĆ, and Maja ZNIKA (2005), Hrvatska gramatika, Školska knjiga, Zagreb, ISBN 9789530400108.
• 3. Cristina BARROS, Dimitra GKATZIA, and Elena LLORET (2017), Inflection generation for Spanish verbs using supervised learning, in Manaal FARUQUI, Hinrich SCHUETZE, Isabel TRANCOSO, and Yadollah YAGHOOBZADEH, editors, Proceedings of the First Workshop on Subword and Character Level Models in NLP, pp. 136-141, Association for Computational Linguistics, Copenhagen, Denmark, doi:10.18653/v1/W17-4120.
• 4. Piotr BOJANOWSKI, Edouard GRAVE, Armand JOULIN, and Tomas MIKOLOV(2017), Enriching word vectors with subword information, Transactions of the Association for Computational Linguistics, pp. 135-146, doi:10.1162/tacl_a_00051.
• 5. Marina DANILEVSKY, Kun QIAN, Ranit AHARONOV, Yannis KATSIS, Ban KAWAS, and Prithviraj SEN (2020), A survey of the state of explainable AI for natural language processing, in Kam-Fai WONG, Kevin KNIGHT, and Hua WU, editors, Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing, pp. 447-459, Association for Computational Linguistics, Suzhou, China.
• 6. Liviu P. DINU, Vlad NICULAE, and Octavia-Maria SULEA (2012), Learning how to conjugate the Romanian verb. Rules for regular and partially irregular verbs, in Walter DAELEMANS, editor, Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics, pp. 524-528, Association for Computational Linguistics, Avignon, France.
• 7. Josef DOBROVSKỲ (1809), Ausführliches Lehrgebäude der Böhmischen Sprache, zur gründlichen Erlernung derselben für Deutsche, zur vollkommenern Kenntniß für Böhmen, J. Herrl, Prague, https://books.google.fr/books?vid=UOM:39015036760190&redir_esc=y.
• 8. Greg DURRETT and John DENERO (2013), Supervised learning of complete morphological paradigms, in Lucy VANDERWENDE, Hal DAUMÉ III, and Katrin KIRCHHOFF, editors, Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 1185-1195, Association for Computational Linguistics, Atlanta, Georgia, https://aclanthology.org/N13-1138.
• 9. Vishal GOYAL and Gurpreet Singh LEHAL (2008), Hindi morphological analyzer and generator, in Preeti R. BAJAJ, Amol Y. DESHMUKH, and Kailash D. JOSHI, editors,2008 First International Conference on Emerging Trendsin Engineering and Technology, pp. 1156-1159, doi:10.1109/ICETET.2008.11.
• 10. Nizar HABASH and Owen RAMBOW (2006), MAGEAD: A morphological analyzer and generator for the Arabic dialects, in Nicoletta CALZOLARI, Claire CARDIE, and Pierre ISABELLE, editors, Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of theAssociation for Computational Linguistics, pp. 681-688, Association for Computational Linguistics, Sydney, Australia, doi:10.3115/1220175.1220261.
• 11. Diederik P. KINGMA and Jimmy BA (2015), ADAM: A method for stochastic optimization, in Yoshua BENGIO and Yann LECUN, editors, 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings, doi:10.48550/arXiv.1412.6980.
• 12. Mikhail KOROBOV (2015), Morphological analyzer and generator for Russian and Ukrainian languages, in Mikhail Yu. KHACHAY, Natalia KONSTANTINOVA, Alexander PANCHENKO, Dmitry IGNATOV, and Valeri G. LABUNETS, editors, Analysis of Images, Social Networks and Texts, pp. 320-332, Springer International Publishing, Cham, doi:10.1007/978-3-319-26123-2_31.
• 13. Gichang LEE, Jaeyun JEONG, Seungwan SEO, Czang Yeob KIM, and Pilsung KANG (2018), Sentiment classification with word localization based on weakly supervised learning with a convolutional neural network, Knowledge-Based Systems, 152(C):70-82, ISSN 0950-7051, doi:10.1016/j.knosys.2018.04.006.
• 14. Horace G. LUNT (2001), Old Church Slavonic grammar, Mouton de Gruyter, The Hague, doi:10.1515/9783110876888.
• 15. Lew R. MICKLESEN (1974), The common Slavic verbal system, in Ladislav MATEJKA, Victor TERRAS, and Anna CIENCALA, editors, Vol. 1 Linguistics and Poetics, chapter American contributions to the Seventh International Congress of Slavists, August 21-27, 1973, pp. 241-274, De Gruyter Mouton, Berlin, Boston, ISBN 9783110873948, doi:10.1515/9783110873948-011.
• 16. Milan MIHALJEVIĆ (2014), Slavenska poredbena gramatika 2. dio: Morfologija, prozodija, slavenska pradomovina., Školska knjiga, Zagreb, ISBN 953-0-30225-8.
• 17. Marko OREŠKOVIĆ, Sandra LOVRENČIĆ, and Mario ESSERT (2018), Croatian Network Lexicon within the Syntactic and Semantic Framework and LLOD Cloud, International Journal of Lexicography, 32(2):207-227, ISSN 0950-3846, doi:10.1093/ijl/ecy024.
• 18. Marko OREŠKOVIĆ, Jakov TOPIĆ, and Mario ESSERT (2016), Croatian linguistic system modules overview, in George Meladze TINATIN MARGALITADZE, editor, Proceedings of the 17th EURALEX International Congress, pp. 280-283, Ivane Javakhishvili Tbilisi University Press, Tbilisi, Georgia, ISBN 978-9941-13-542-2.
• 19. Adam PASZKE, Sam GROSS, Francisco MASSA, Adam LERER, James BRADBURY, Gregory CHANAN, Trevor KILLEEN, Zeming LIN, Natalia GIMELSHEIN, Luca ANTIGA, Alban DESMAISON, Andreas KOPF, Edward YANG, Zachary DEVITO, Martin RAISON, Alykhan TEJANI, Sasank CHILAMKURTHY, Benoit STEINER, Lu FANG, Junjie BAI, and Soumith CHINTALA (2019), Py Torch: An imperative style, high-performance deep learning library, in Hanna M. WALLACH, Hugo LAROCHELLE, Alina BEYGELZIMER, Florence D'ALCHÉ-BUC, Edward A. FOX, and Roman GARNETT, editors, Advances in Neural Information Processing Systems 32, pp. 8024-8035, Curran Associates, Inc., doi:10.48550/arXiv.1912.01703.
• 20. Ida RAFFAELLI, Marko TADIĆ, Božo BEKAVAC, and Željko AGIĆ (2008), Building croatian wordnet, in Attila TÁNACS, Dóra CSENDES, Veronica VINCZE, Christiane FELLBAUM, and Piek VOSSEN, editors, Proceedings of the 4th Global Word Net Conference (GWC 2008), pp. 349-359, Global Word Net Association, Szeged, Hungary, ISBN 978-963-482-854-9.
• 21. Josip SILIĆ and Ivo PRANJKOVIĆ (2005), Gramatika hrvatskoga jezika, Školska knjiga, Zagreb.
• 22. Octavia-Maria ŞULEA and Steve YOUNG (2019), Unsupervised inflection generation using neural language modelling, in Ignacio ROJAS, Gonzalo JOYA, and Andreu CATALA, editors, Advances in Computational Intelligence, pp. 668-678, Springer International Publishing, Cham, doi:10.48550/arXiv.1912.01156.
• 23. Krešimir ŠOJAT, Matea SREBAČIĆ, and Marko TADIĆ (2012), Derivational andsemantic relations of Croatian verbs, Journal of Language Modelling, 0(1):111-142, ISSN 2299-8470, doi:10.15398/jlm.v0i1.34.
• 24. Richard Howard WICENTOWSKI (2002), Modeling and learning multilingual inflectional morphology in a minimally supervised framework, Ph.D. thesis, The Johns Hopkins University, https://www.cs.swarthmore.edu/~richardw/pubs/thesis.pdf.
• 25. Shijie WU, Ryan COTTERELL, and Mans HULDEN (2021), Applying the transformer to character-level transduction, in Paola MERLO, Jorg TIEDEMANN, and Reut TSARFATY, editors, Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pp. 1901-1907, Association for Computational Linguistics, Online, doi:10.18653/v1/2021.eacl-main.163.
• 26. Andrea ZIELINSKI, Christian SIMON, and Tilman WITTL (2009), Morphisto: Service-oriented open source morphology for German, in Cerstin MAHLOW and Michael PIOTROWSKI, editors, State of the Art in Computational Morphology, pp. 64-75, Springer Berlin Heidelberg, Berlin, Heidelberg, doi:10.1007/978-3-642-04131-0_5.