Geodesic
Syntax transfer to Kyrgyz using the treebank translation method
Zapiski Nauchnykh Seminarov POMI, Investigations on applied mathematics and informatics. Part IV, Tome 540 (2024), pp. 252-275 Cet article a éte moissonné depuis la source Math-Net.Ru

Voir la notice du chapitre de livre

Kyrgyz is a less-resourced language and requires significant effort to create high-quality syntax corpora (treebanks). In this work, we propose an approach that simplifies the development of a treebank for the Kyrgyz language. We present a tool for transferring syntactic annotations from the Turkish language to Kyrgyz based on the treebank translation method. We evaluate the efficiency of our approach using the TueCL treebank. Results show that our method provides higher quality of syntactic annotation compared to a monolingual model trained on the Kyrgyz KTMU treebank. Moreover, in this work we propose a method to evaluate the complexity of manual annotation for the resulting syntax trees, contributing to further optimization of the annotation process. 
@article{ZNSL_2024_540_a13,
     author = {A. Alekseev and A. Tillabaeva and G. Dzh. Kabaeva and S. I. Nikolenko},
     title = {Syntax transfer to {Kyrgyz} using the treebank translation method},
     journal = {Zapiski Nauchnykh Seminarov POMI},
     pages = {252--275},
     year = {2024},
     volume = {540},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/ZNSL_2024_540_a13/}
}
TY  - JOUR
AU  - A. Alekseev
AU  - A. Tillabaeva
AU  - G. Dzh. Kabaeva
AU  - S. I. Nikolenko
TI  - Syntax transfer to Kyrgyz using the treebank translation method
JO  - Zapiski Nauchnykh Seminarov POMI
PY  - 2024
SP  - 252
EP  - 275
VL  - 540
UR  - http://geodesic.mathdoc.fr/item/ZNSL_2024_540_a13/
LA  - ru
ID  - ZNSL_2024_540_a13
ER  - 
%0 Journal Article
%A A. Alekseev
%A A. Tillabaeva
%A G. Dzh. Kabaeva
%A S. I. Nikolenko
%T Syntax transfer to Kyrgyz using the treebank translation method
%J Zapiski Nauchnykh Seminarov POMI
%D 2024
%P 252-275
%V 540
%U http://geodesic.mathdoc.fr/item/ZNSL_2024_540_a13/
%G ru
%F ZNSL_2024_540_a13
A. Alekseev; A. Tillabaeva; G. Dzh. Kabaeva; S. I. Nikolenko. Syntax transfer to Kyrgyz using the treebank translation method. Zapiski Nauchnykh Seminarov POMI, Investigations on applied mathematics and informatics. Part IV, Tome 540 (2024), pp. 252-275. http://geodesic.mathdoc.fr/item/ZNSL_2024_540_a13/

[1] UniversalDependencies/tools/eval.py: UD Evaluation Script on GitHub, , 2024 https://github.com/UniversalDependencies/tools/blob/19c980e95ed0944dd5ecd262322403f8a77cee69/eval.py

[2] J. Achiam, S. Adler, S. Agarwal, et al., GPT-4 technical report, 2023, arXiv: 2303.08774

[3] Z. Agić, A. Johannsen, B. Plank, et al., “Multilingual Projection for Parsing Truly Low-Resource Languages”, Transactions of the Association for Computational Linguistics, 2016, no. 4, 301–312

[4] A. Furkan, B. Chontaeva, C. Cöltekin, et al., Unifying the Annotations in Turkic Universal Dependencies Treebanks, 2nd UniDive Workshop Theses (Online), 2024

[5] A. Alekseev, alexeyev/apertium2ud: mapping tagsets, 2023

[6] A. Alekseev, T. Turatali, “KyrgyzNLP: Challenges, Progress, and Future”, Proceedings of the 12th International Conference on Analysis of Images, Social Networks, and Texts (AIST 2024), Lecture Notes in Computer Science, 15419, Springer, 2024 (to appear) | MR

[7] W. Ammar, G. Mulcaire, M. Ballesteros, et al., “Many Languages, One Parser”, Transactions of the Association for Computational Linguistics, 2016, no. 4, 431–444 | DOI

[8] I. Benli, UD_Kyrgyz-KTMU: UD for Kyrgyz, 2023 https://github.com/UniversalDependencies/UD_Kyrgyz-KTMU/

[9] I. Benli, B. Sharshembaev, “Dependency Parsing Based Treebank for Kyrgyz Language”, Ymer, 23:7 (2024), 325–342

[10] P.F. Brown, S.A. Della Pietra, V.J. Della Pietra, R.L. Mercer, “The mathematics of statistical machine translation: Parameter estimation”, Computational Linguistics, 19:2 (1993), 263–311

[11] A. Das, S. Sarkar, “A Survey of the Model Transfer Approaches to Cross-Lingual Dependency Parsing”, ACM Transactions on Asian and Low-Resource Language Information Processing, 19:5 (2020), 1–60

[12] M.-C. de Marneffe, C.D. Manning, J. Nivre, D. Zeman, “Universal Dependencies”, Computational Linguistics, 47:2 (2021), 255–308

[13] J. Devlin, M.-W. Chang, K. Lee, K. Toutanova, “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding”, Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2019, 4171–4186 | MR

[14] Z.-Y. Dou, G. Neubig, “Word Alignment by Fine-tuning Embeddings on Parallel Corpora”, Conference of the European Chapter of the Association for Computational Linguistics (EACL), 2021

[15] G. Durrett, A. Pauls, D. Klein, “Syntactic transfer using a bilingual lexicon”, Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, 2012, 1–11

[16] J. Heinecke, “ConlluEditor: a fully graphical editor for Universal Dependencies treebank files”, Universal Dependencies Workshop (Paris), 2019 | Zbl

[17] J.E. Hopcroft, R.M. Karp, “An $n^{5/2}$ algorithm for maximum matchings in bipartite graphs”, SIAM Journal on Computing, 2:4 (1973), 225–231 | DOI | MR | Zbl

[18] R. Hwa, Ph. Resnik, A. Weinberg, C. Cabezas, O. Kolak, “Bootstrapping parsers via syntactic projection across parallel texts”, Natural Language Engineering, 11:3 (2005), 311–325 | DOI

[19] M.J. Sabet, Ph. Dufter, F. Yvon, H. Schütze, “SimAlign: High Quality Word Alignments without Parallel Training Data using Static and Contextualized Embeddings”, Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Findings, 2020, 1627–1643

[20] A. Conneau, Unsupervised cross-lingual representation learning at scale, 2019, arXiv: 1911.02116

[21] Y. Liu, M. Ott, N. Goyal, J. Du, M. Joshi, D. Che, O. Levy, M. Lewis, L. Zettlemoyer, V. Stoyanov, RoBERTa: A Robustly Optimized BERT Pretraining Approach, 2019, arXiv: 1907.11692

[22] R. McDonald, J. Nivre, Y. Quirmbach-Brundage, et al., “Universal Dependency Annotation for Multilingual Parsing”, Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, v. 2, Short Papers, 2013, 92–97

[23] J. Mirzakhalov, A. Babu, A. Kunafin, A. Wahab, B. Moydinboyev, S. Ivanova, M. Uzokova, Sh. Pulatova, D. Ataman, J. Kreutzer, F. M. Tyers, O. Firat, J. Licato, S. Chellappan, “Evaluating Multiway Multilingual NMT in the Turkic Languages”, Proceedings of the Sixth Conference on Machine Translation, 2021, 518–530

[24] J. Nivre, “Towards a universal grammar for natural language processing”, International conference on intelligent text processing and computational linguistics, Springer, 2015, 3–16

[25] P. Qi, Y. Zhang, Y. Zhang, J. Bolton, C.D. Manning, “Stanza: A Python Natural Language Processing Toolkit for Many Human Languages”, Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, 2020 | MR

[26] M.S. Rasooli, M. Collins, “Density-Driven Cross-Lingual Transfer of Dependency Parsers”, Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (Lisbon, Portugal), 2015, 328–338 | DOI

[27] P. Stenetorp, S. Pyysalo, G. Topić, T. Ohta, S. Ananiadou, J. Tsujii, “brat: a Web-based Tool for NLP-Assisted Text Annotation”, Proceedings of the Demonstrations Session at EACL 2012 (Avignon, France), 2012

[28] M. Straka, “UDPipe 2.0 Prototype at CoNLL 2018 UD Shared Task”, Proceedings of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies (Brussels, Belgium), 2018, 197–207

[29] U. Sulubacak, G. Eryi{ğ}it, “Implementing universal dependency, morphology, and multiword expression annotation standards for Turkish language processing”, Turkish Journal of Electrical Engineering and Computer Sciences, 26:3 (2018), 1662–1672

[30] U. Sulubacak, G. Eryi{ğ}it, T. Pamay, “IMST: A revisited Turkish dependency treebank”, The 1st International Conference on Turkic Computational Linguistics, Ege University Press, 2016, 1–6

[31] U. Sulubacak, M. Gök{\i}rmak, F. M. Tyers, {Ç}. {Ç}öltekin, J. Nivre, and G. Eryi{ğ}it, “Universal dependencies for Turkish”, Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics, Technical papers, 2016, 3444–3454

[32] A. Søgaard, “Data point selection for cross-language adaptation of dependency parsers”, The 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Short Papers, v. 2, 2011, 682–686

[33] L. Tesnière, Éléments de syntaxe structurale, Klincksieck, Paris, 1959

[34] J. Tiedemann, Ž. Agić, J. Nivre, “Treebank Translation for Cross-Lingual Parser Induction”, Proceedings of the Eighteenth Conference on Computational Natural Language Learning (Ann Arbor, Michigan), 2014, 130–140 | DOI

[35] A. Tillabaeva, Syntactic Transfer Based on the Polivariant Parallel Kyrgyz-Russian Corpus Manas, Master's thesis, HSE University, Moscow, Russia, 2024 https://www.hse.ru/en/ma/ling/students/diplomas/930858853

[36] U. Türk, F. Atmaca, Ş. B. Özateş, G. Berk, S. T. Bedir, A. Köksal, B. Ö. Başaran, T. Güngör, A. Özgür, “Resources for Turkish Dependency Parsing: Introducing the BOUN Treebank and the BoAT Annotation Tool”, Language Resources and Evaluation, 56:1 (2022), 259–307 | DOI

[37] F. M. Tyers, M. Sheyanova, J .N. Washington, “UD Annotatrix: An Annotation Tool for Universal Dependencies”, Proceedings of the 16th International Workshop on Treebanks and Linguistic Theories, TLT16, 2018, 10–17

[38] Y. Veitsman, Recent Advancements and Challenges of Turkic Central Asian Language Processing, 2024, arXiv: 2407.05006 | MR

[39] P. Virtanen, R. Gommers, T. E. Oliphant, et al., “SciPy 1.0: Fundamental Algorithms for Scientific Computing in Python”, Nature Methods, 17 (2020), 261–272 | DOI

[40] J. Washington, {Ç}. {Ç}öltekin, F. Akkurt, B. Chontaeva, S. Eslami, G. Jumalieva, A. Kasieva, A. Kuzgun, B. Mar{ş}an, Ch. Taguchi, “Strategies for the Annotation of Pronominalised Locatives in Turkic Universal Dependency Treebanks”, Proc. Joint Workshop on Multiword Expressions and Universal Dependencies (MWE-UD), LREC-COLING 2024, 2024, 207–219

[41] J. N. Washington, M. Ipasov, F. M. Tyers, “A finite-state morphological transducer for Kyrgyz”, LREC, 2012, 934–940

[42] H. Zhao, Y. Song, Ch. Kit, G. Zhou, “Cross-language dependency parsing using a bilingual lexicon”, Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP, Suntec (Singapore), 2009, 55–63

[43] G. K. Dzhumalieva, A. A. Kasieva, S. Zh. Musazhanova, “Adaptatsiya terminov veb-proekta «Universalnye zavisimosti» na kyrgyzskii yazyk”, Vestnik KRSU, 23:6 (2023), 71–75

[44] A. A. Kasieva, G. K. Dzhumalieva, A. Tompson, et al., “Problemy kyrgyzskoi sintaksicheskoi annotatsii v freimvorke Universal Dependencies”, Proceedings of TurkLang-2023 (Bukhara), 2023, 189–216

[45] S. Zh. Musazhanova, A. A. Kasieva, G. K. Dzhumalieva, “Sintaksicheskaya annotatsiya kyrgyzskogo yazyka na osnove novosozdannogo korpusa”, Vestnik Issyk-Kulskogo universiteta, 54:2 (2023), 140–148