Compartir recursos lingüístics de qualitat en l’àmbit jurídic per desenvolupar la traducció automàtica neuronal per a les llengües europees amb pocs recursos

• Autores: Petra Bago, Sheila Castilho, Edoardo Celeste, Jane Dunne, Federico Gaspari, Níels Rúnar Gíslason, Andre Kåsen, Filip Klubicka, Gauti Kristmannsson, Helen McHugh, Róisín Moran, Órla Ní Loinsigh, Jon-arild Olsen, Carla Parra Escartín, Akshai Ramesh, Natália Resende, Páraic Sheridan, Andy Way
• Localización: Revista de llengua i dret, ISSN-e 2013-1453, ISSN 0212-5056, Nº. 78, 2022, págs. 9-34
• Idioma: varios idiomas
• DOI: 10.2436/rld.i78.2022.3741
• Enlaces
  • Texto completo (pdf)
• Resumen

  • En aquest article es presenten algunes de les reeixides principals del projecte PRINCIPLE, finançat per la Unió Europea, en relació amb la recopilació de recursos lingüístics (RL) de qualitat en l’àmbit jurídic per a quatre llengües europees amb pocs recursos: el croat, l’irlandès, el noruec i l’islandès. Després d’il·lustrar la importància d’aquest treball per desenvolupar tecnologies de la traducció en el marc de la Unió Europea i l’Espai Econòmic Europeu, en l’article es descriuen els passos principals per recollir dades, conservar i compartir els RL recopilats amb l’ajuda de proveïdors de dades públics i privats. A continuació, es descriuen el procés de desenvolupament i les característiques clau dels motors de traducció automàtica (TA) neuronal d’última generació adaptats al context jurídic que s’han creat amb aquestes dades. Els sistemes de TA es van avaluar amb una combinació de mètodes automàtics i humans per validar la qualitat dels RL recollits en el projecte i, més endavant, els RL de qualitat es van compartir amb el públic general a través del repositori ELRC-SHARE. L’article debat les dificultats més importants amb què ha topat aquest treball i s’hi subratlla la importància i els avantatges primordials de compartir RL digitals de qualitat

• Referencias bibliográficas
  • Bago, Petra, Dunne, Jane, Gaspari, Federico, Kåsen, Andre, Kristmannsson, Gauti, McHugh, Helen, Olsen, Jon Arild, Sheridan, Dana D., Sheridan,...
  • Bago, Petra, Castilho, Sheila, Dunne, Jane, Gaspari, Federico, Kåsen, Andre, Kristmannsson, Gauti, Olsen, Jon Arild, Resende, Natalia, Rúnar,...
  • Banerjee Satanjeev, & Lavie, Alon. (2005). METEOR: An automatic metric for MT evaluation with improved correlation with human judgments....
  • Bojar Ondřej, Graham, Yvette, & Kamran, Amir. (2017). Results of the WMT17 Metrics Shared Task. In Ondřej Bojar, Christian Buck, Rajen...
  • Bowker Lynne, & Ciro, Jairo Buitrago. (2019). Machine translation and global research: Towards improved machine translation literacy in...
  • Callison-Burch Chris, Osborne, Miles, & Koehn, Philipp. (2006). Re-evaluating the role of BLEU in machine translation research. In Diana...
  • Castilho, Sheila, Doherty, Stephen, Gaspari, Federico, & Moorkens, Joss. (2018). Approaches to human and machine translation quality assessment....
  • Chen, Boxing, Cherry, Colin, Foster, George, & Larkin, Samuel. (2017). Cost weighting for neural machine translation domain adaptation....
  • Chu, Chenhui, Dabre, Raj, & Kurohashi, Sadao. (2017). An empirical comparison of domain adaptation methods for neural machine translation....
  • Chu, Chenhui, & Wang, Rui. (2018). A survey of domain adaptation for neural machine translation. In Emily M. Bender, Leon Derczynski,...
  • Chu, Chenhui, Dabre, Raj, & Kurohashi, Sadao. (2018). A comprehensive empirical comparison of domain adaptation methods for neural machine...
  • Clark, Jonathan H., Dyer, Chris, Lavie, Alon, & Smith, Noah A. (2011). Better hypothesis testing for statistical machine translation:...
  • & Rada Mihalcea (Eds.), Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies...
  • Denkowski, Michael, & Lavie, Alon. (2012). Challenges in predicting machine translation utility for human post-editors. Proceedings of...
  • Eide, Kristine, Kåsen, Andre, & Dale, Ingerid Løyning. (2022). D1.26: Report on the Norwegian language. European Language Equality Project.
  • Etchegoyhen, Thierry, Fernández Torné, Anna, Azpeitia, Andoni, Martínez García, Eva, & Matamala, Anna. (2018). Evaluating domain adaptation...
  • Gaspari, Federico, Way, Andy, Dunne, Jane, Rehm, Georg, Piperidis, Stelios, & Giagkou, Maria. (2022). D1.1: Digital language equality...
  • Gupta, Rohit, Lambert, Patrik, Nath Patel, Raj, & Tinsley, John. (2019). Improving robustness in real-world neural machine translation...
  • Kahaner, Steven. (2005). Issues in legal translation. Ccaps Translation and Localization, 1–3.
  • Klubička, Filip, Kasunić, Lorena, Blazsetin, Danijel, & Bago, Petra. (2022). Challenges of building domainspecific parallel corpora from...
  • Koehn, Philipp, & Ulrich, Germann. (2014). The impact of machine translation quality on human post-editing. In Ulrich Germann, Michael...
  • Lavie, Alon, & Agarwal, Abhaya. (2007). METEOR: An automatic metric for MT evaluation with high levels of correlation with human judgments....
  • Läubli, Samuel, Amrhein, Chantal, Düggelin, Patrick, Gonzalez, Beatriz, Zwahlen, Alena, & Volk, Martin. (2019). Post-editing productivity...
  • Lommel, Arle, Uszkoreit, Hans, & Burchardt, Aljoscha. (2014). Multidimensional quality metrics (MQM): A framework for declaring and describing...
  • Lynn, Teresa. (2022). D1.20: Report on the Irish language. European Language Equality Project.
  • O’Brien, Sharon, & Ehrensberger-Dow, Maureen. (2020). MT literacy – A cognitive view. Translation, Cognition & Behavior, 3(2), 145–164....
  • Papineni, Kishore, Roukos, Salim, Ward, Todd, & Zhu, Wei-Jing. (2002). BLEU: A method for automatic evaluation of machine translation....
  • Plitt, Mirko, & Masselot, François. (2010). A productivity test of statistical machine translation post-editing in a typical localisation...
  • Popović, Maja. (2015). ChrF: Character n-gram F-score for automatic MT evaluation. In Ondřej Bojar, Rajan Chatterjee, Christian Federmann,...
  • Post, Matt. (2018). A call for clarity in reporting BLEU scores. In Ondřej Bojar, Rajen Chatterjee, Christian Federmann, Mark Fishel, Yvette...
  • Radding, Charles, & Ciaralli, Antonio. (2006). The corpus iuris civilis in the Middle Ages: Manuscripts and transmission from the sixth...
  • Rögnvaldsson, Eiríkur. (2022). D1.19: Report on the Icelandic language. European Language Equality Project.
  • Sennrich, Rico, Haddow, Barry, & Birch, Alexandra. (2016). Neural machine translation of rare words with subword units. In Katrin Erk,...
  • Snover, Matthew, Dorr, Bonnie, Schwartz, Richard, Micciulla, Linnea, & Makhoul, John. (2006). A study of translation edit rate with targeted...
  • Tadić, Marko. (2022). D1.7: Report on the Croatian language. European Language Equality Project.
  • Thompson, Brian, & Koehn, Phillip. (2019). Vecalign: Improved sentence alignment in linear time and space. In Sebastian Padó, & Ruihong...
  • Varga, Dániel, Németh, László, Halácsy, Péter, Kornai, András, Trón, Viktor, & Nagy, Viktor. (2005). Parallel corpora for medium density...
  • Vaswani, Ashish, Shazeer, Noam, Parmar, Niki, Uszkoreit, Jakob, Jones, Llion, Gomez, Aidan N., Kaiser, Lukasz, & Polosukhin, Illia. (2017)....
  • Way, Andy. (2018). Quality expectations of machine translation. In Joss Moorkens, Sheila Castilho, Federico Gaspari, & Stephen Doherty...
  • Way, Andy, & Gaspari, Federico. (2019). PRINCIPLE: Providing resources in Irish, Norwegian, Croatian and Icelandic for the purposes of...
  • Translation.
  • Way Catherine. (2016). The challenges and opportunities of legal translation and translator training in the 21st century. International Journal...
  • Wolff, Leon. (2011). Legal translation. In Kirsten Malmkjær, & Kevin Windle (eds.), The Oxford handbook of translation studies (pp. 228–242)....
  • Zhang, Mike, & Toral, Antonio. (2019). The effect of translationese in machine translation test sets. In Ondřej Bojar, Rajen Chatterjee,...