Attention mechanism and skip-gram embedded phrases-Reference-Cited by-同舟云学术

Attention mechanism and skip-gram embedded phrases

Published:2023-01-09 Issue: Volume:52 Page:318-350
ISSN:2391-4491
Container-title:Comparative Legilinguistics
language:
Short-container-title:cl

Author:

Krimpas Panagiotis^ORCID,Valavani Christina^ORCID

Abstract

This article examines common translation errors that occur in the translation of legal texts. In particular, it focuses on how German texts containing legal terminology are rendered into Modern Greek by the Google translation machine. Our case study is the Google-assisted translation of the original (German) version of the Constitution of the Federal Republic of Germany into Modern Greek. A training method is proposed for phrase extraction based on the occurrence frequency, which goes through the Skip-gram algorithm to be then integrated into the Self Attention Mechanism proposed by Vaswani et al. (2017) in order to minimise human effort and contribute to the development of a robust machine translation system for multi-word legal terms and special phrases. This Neural Machine Translation approach aims at developing vectorised phrases from large corpora and process them for translation. The research direction is to increase the in-domain training data set and enrich the vector dimension with more information for legal concepts (domain specific features).

Publisher

Adam Mickiewicz University Poznan

Subject

Law,Linguistics and Language,Language and Linguistics

Reference27 articles.

1. Bahdanau, Dzmitry, Kyunghyun Cho, and Yoshua Bengio. 2016. Neural machine translation by jointly learning to align and translate. In Proceedings of the 3rd International Conference on Learning Representations, ICLR 2015. arXiv:1409.0473v7 [cs.CL]. DOI: https://doi.org/10.48550/arXiv.1409.0473.

2. Bojanowski, Piotr, Edouard Grave, Armand Joulin, and Tomas Mikolov. 2017. Enriching word vectors with subword information. Transactions of the Association for Computational Linguistics 5: 135–46. https://aclanthology.org/Q17-1010.pdf (accessed December 28, 2022).

3. Bouma, Gerlof. 2009. Normalized (Pointwise) Mutual information in collocation extraction. In From Form to Meaning: Processing Texts Automatically: Proceedings of the Biennial GSCL Conference 2009, eds. Christian Chiarcos, Richard Eckart de Castilho and Manfred Stede, 31–40. Tübingen: Gunter Narr.

4. Camacho-Collados, José, and Mohammad Taher Pilehvar. 2018. From word to sense embeddings: A survey on vector representations of meaning. Journal of Artificial Intelligence Research 63: 743–88. DOI: https://doi.org/10.1613/jair.1.11259.

5. Diniz da Costa, Alexandre, Mateus Coutinho Marim, Ely Edison da Silva Matos, and Tiago Timponi Torrent. 2022. Domain Adaptation in Neural Machine Translation using a Qualia-Enriched FrameNet. In Proceedings of the 13th Conference on Language Resources and Evaluation (LREC 2022), eds. Nicoletta Calzolari, Frédéric Béchet, Philippe Blache, Khalid Choukri, Christopher Cieri, Thierry Declerck, Sara Goggi, Hitoshi Isahara, Bente Maegaard, Joseph Mariani, Hélène Mazo, Jan Odijk and Stelios Piperidis, 1–12. Paris: European Language Resources Association (ELRA). http://www.lrec-conf.org/proceedings/lrec2022/LREC-2022.pdf (accessed December 28, 2022).