{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T06:14:22Z","timestamp":1765260862276,"version":"3.46.0"},"reference-count":97,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T00:00:00Z","timestamp":1754524800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T00:00:00Z","timestamp":1754524800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"TANDO","award":["KK-2020\/00074","KK-2020\/00074","KK-2020\/00074","KK-2020\/00074","KK-2020\/00074","KK-2020\/00074","KK-2020\/00074","KK-2020\/00074","KK-2020\/00074"],"award-info":[{"award-number":["KK-2020\/00074","KK-2020\/00074","KK-2020\/00074","KK-2020\/00074","KK-2020\/00074","KK-2020\/00074","KK-2020\/00074","KK-2020\/00074","KK-2020\/00074"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Lang Resources & Evaluation"],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1007\/s10579-025-09854-z","type":"journal-article","created":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T07:18:09Z","timestamp":1754551089000},"page":"3699-3739","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["TANDO+: corpus and baselines for document-level machine translation in Basque\u2013Spanish and Basque\u2013French"],"prefix":"10.1007","volume":"59","author":[{"given":"Harritxu","family":"Gete","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thierry","family":"Etchegoyhen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gorka","family":"Labaka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ander","family":"Corral","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xabier","family":"Saralegi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nora","family":"Aranberri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Ponce","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Igor Ellakuria","family":"Santos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maite","family":"Martin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,8,7]]},"reference":[{"key":"9854_CR1","unstructured":"Agrawal, R., Turchi, M., & Negri, M. (2018). Contextual handling in neural machine translation: Look behind, ahead and on both sides. In Proceedings of the 21st Annual Conference of the European Association for Machine Translation (EAMT)."},{"key":"9854_CR2","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1007\/s10590-019-09234-9","volume":"33","author":"A Azpeitia","year":"2019","unstructured":"Azpeitia, A., & Etchegoyhen, T. (2019). Efficient document alignment across scenarios. Machine Translation, 33, 205\u2013237.","journal-title":"Machine Translation"},{"key":"9854_CR3","doi-asserted-by":"crossref","unstructured":"Azpeitia, A., Etchegoyhen, T., & Mart\u00ednez\u00a0Garcia, E. (2017). Weighted set-theoretic alignment of comparable sentences. In Proceedings of the Tenth Workshop on Building and Using Comparable Corpora, pp. 41\u201345, Vancouver, Canada.","DOI":"10.18653\/v1\/W17-2508"},{"key":"9854_CR4","doi-asserted-by":"crossref","unstructured":"Balloccu, S., Schmidtov\u00e1, P., Lango, M., & Du\u0161ek, O. (2024). Leak, cheat, repeat: Data contamination and evaluation malpractices in closed-source llms. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 67\u201393.","DOI":"10.18653\/v1\/2024.eacl-long.5"},{"key":"9854_CR5","doi-asserted-by":"crossref","unstructured":"Barrault, L., Bojar, O., Costa-juss\u00e0, M.\u00a0R., Federmann, C., Fishel, M., Graham, Y., Haddow, B., Huck, M., Koehn, P., Malmasi, S., Monz, C., M\u00fcller, M., Pal, S., Post, M., & Zampieri, M. (2019). Findings of the 2019 conference on machine translation (WMT19). In Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1), pp. 1\u201361, Florence, Italy. Association for Computational Linguistics.","DOI":"10.18653\/v1\/W19-5301"},{"key":"9854_CR6","doi-asserted-by":"crossref","unstructured":"Bawden, R., Sennrich, R., Birch, A., & Haddow, B. (2018). Evaluating discourse phenomena in neural machine translation. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pp. 1304\u20131313, New Orleans, Louisiana. Association for Computational Linguistics.","DOI":"10.18653\/v1\/N18-1118"},{"key":"9854_CR7","unstructured":"Castilho, S., Mallon, C., Meister, R., & Yue, S. (2023). Do online machine translation systems care for context? What about a GPT model? In Proceedings of the 24nd Annual Conference of the European Association for Machine Translation, pp. 393\u2013417, Tampere, Finland. European Association for Machine Translation."},{"issue":"2","key":"9854_CR8","first-page":"243","volume":"4","author":"T Etchegoyhen","year":"2016","unstructured":"Etchegoyhen, T., & Azpeitia, A. (2016). A portable method for parallel and comparable document alignment. Baltic Journal of Modern Computing, 4(2), 243\u2013255.","journal-title":"Baltic Journal of Modern Computing"},{"key":"9854_CR9","doi-asserted-by":"crossref","unstructured":"Etchegoyhen, T. and Azpeitia, A. (2016b). Set-theoretic alignment for comparable corpora. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, volume 1: Long Papers, pp. 2009\u20132018, Berlin, Germany.","DOI":"10.18653\/v1\/P16-1189"},{"key":"9854_CR10","unstructured":"Etchegoyhen, T., Azpeitia, A., & P\u00e9rez, N. (2016). Exploiting a large strongly comparable corpus. In Proceedings of the Tenth International Conference on Language Resources and Evaluation, Portoro\u017e, Slovenia."},{"key":"9854_CR11","unstructured":"Etchegoyhen, T. and Gete, H. (2020). Handle with care: A case study in comparable corpora exploitation for neural machine translation. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pp. 3799\u20133807, Marseille, France. European Language Resources Association."},{"key":"9854_CR12","doi-asserted-by":"crossref","unstructured":"Etxaniz, J., Sainz, O., Miguel, N., Aldabe, I., Rigau, G., Agirre, E., Ormazabal, A., Artetxe, M., & Soroa, A. (2024). Latxa: An open language model and evaluation suite for basque. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 14952\u201314972.","DOI":"10.18653\/v1\/2024.acl-long.799"},{"key":"9854_CR13","unstructured":"Falc\u00e3o, J., Borg, C., Aranberri, N., & Abela, K. (2024). COMET for low-resource machine translation evaluation: A case study of English-Maltese and Spanish-Basque. In Calzolari, N., Kan, M.-Y., Hoste, V., Lenci, A., Sakti, S., and Xue, N., eds, Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pp. 3553\u20133565, Torino, Italia. ELRA and ICCL."},{"key":"9854_CR14","doi-asserted-by":"crossref","unstructured":"Fernandes, P., Yin, K., Liu, E., Martins, A. F.\u00a0T., & Neubig, G. (2023). When does translation require context? A data-driven, multilingual exploration.","DOI":"10.18653\/v1\/2023.acl-long.36"},{"key":"9854_CR15","doi-asserted-by":"crossref","unstructured":"Fernandes, P., Yin, K., Neubig, G., & Martins, A. F.\u00a0T. (2021). Measuring and increasing context usage in context-aware machine translation. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 6467\u20136478, Online. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2021.acl-long.505"},{"key":"9854_CR16","unstructured":"Freitag, M., Rei, R., Mathur, N., Lo, C.-k., Stewart, C., Avramidis, E., Kocmi, T., Foster, G., Lavie, A., & Martins, A.\u00a0F. (2022). Results of wmt22 metrics shared task: Stop using bleu\u2013neural metrics are better and more robust. In Proceedings of the Seventh Conference on Machine Translation (WMT), pp. 46\u201368."},{"key":"9854_CR17","doi-asserted-by":"crossref","unstructured":"Gete, H. & Etchegoyhen, T. (2022). Making the most of comparable corpora in neural machine translation: A case study. Language Resources and Evaluation, pp. 1\u201329.","DOI":"10.1007\/s10579-021-09572-2"},{"key":"9854_CR18","unstructured":"Gete, H., Etchegoyhen, T., & Labaka, G. (2023). What works when in context-aware neural machine translation? In Proceedings of the 24nd Annual Conference of the European Association for Machine Translation, pp. 147\u2013156, Tampere, Finland. European Association for Machine Translation."},{"key":"9854_CR19","unstructured":"Gete, H., Etchegoyhen, T., Ponce, D., Labaka, G., Aranberri, N., Corral, A., Saralegi, X., Ellakuria, I., & Martin, M. (2022). TANDO: A corpus for document-level machine translation. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pp. 3026\u20133037, Marseille, France. European Language Resources Association."},{"key":"9854_CR20","unstructured":"Gong, Z., Zhang, M., & Zhou, G. (2011). Cache-based document-level statistical machine translation. In Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing, pp. 909\u2013919, Edinburgh, Scotland, UK. Association for Computational Linguistics."},{"key":"9854_CR21","unstructured":"Grattafiori, A., Dubey, A., Jauhri, A., Pandey, A., Kadian, A., Al-Dahle, A., Letman, A., Mathur, A., Schelten, A., Vaughan, A., Yang, A., Fan, A., Goyal, A., Hartshorn, A., Yang, A., Mitra, A., Sravankumar, A., Korenev, A., Hinsvark, A., \u2026 Ma, Z. (2024). The llama 3 herd of models. Preprint at arXiv preprintarXiv:2407.21783."},{"key":"9854_CR22","unstructured":"Hardmeier, C. and Federico, M. (2010). Modelling pronominal anaphora in statistical machine translation. In Proceedings of the 7th International Workshop on Spoken Language Translation: Papers, pp. 283\u2013289, Paris, France."},{"key":"9854_CR23","unstructured":"Hendy, A., Abdelrehim, M., Sharaf, A., Raunak, V., Gabr, M., Matsushita, H., Kim, Y.\u00a0J., Afify, M., & Awadalla, H.\u00a0H. (2023). How good are gpt models at machine translation? A comprehensive evaluation."},{"key":"9854_CR24","doi-asserted-by":"crossref","unstructured":"Herold, C. and Ney, H. (2023). Improving long context document-level machine translation.","DOI":"10.18653\/v1\/2023.codi-1.15"},{"issue":"2","key":"9854_CR25","first-page":"3","volume":"1","author":"EJ Hu","year":"2022","unstructured":"Hu, E. J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., & Chen, W. (2022). Lora: Low-rank adaptation of large language models. ICLR, 1(2), 3.","journal-title":"ICLR"},{"key":"9854_CR26","doi-asserted-by":"crossref","unstructured":"Huang, Z., Wang, L., Liu, S., & Wong, D.\u00a0F. (2023). How does pretraining improve discourse-aware translation?","DOI":"10.21437\/Interspeech.2023-1068"},{"key":"9854_CR27","unstructured":"Huo, J., Herold, C., Gao, Y., Dahlmann, L., Khadivi, S., & Ney, H. (2020). Diving deep into context-aware neural machine translation. In Proceedings of the Fifth Conference on Machine Translation, pp. 604\u2013616, Online. Association for Computational Linguistics."},{"key":"9854_CR28","unstructured":"Hwang, Y., Yun, H., & Jung, K. (2021). Contrastive learning for context-aware neural machine translation using coreference information. In Proceedings of the Sixth Conference on Machine Translation, pp. 1135\u20131144, Online. Association for Computational Linguistics."},{"key":"9854_CR29","unstructured":"Jean, S., Lauly, S., Firat, O., & Cho, K. (2017a). Does neural machine translation benefit from larger context? CoRR, abs\/1704.05135."},{"key":"9854_CR30","doi-asserted-by":"crossref","unstructured":"Jean, S., Lauly, S., Firat, O., & Cho, K. (2017b). Neural machine translation for cross-lingual pronoun prediction. In Proceedings of the Third Workshop on Discourse in Machine Translation, pp. 54\u201357, Copenhagen, Denmark. Association for Computational Linguistics.","DOI":"10.18653\/v1\/W17-4806"},{"key":"9854_CR31","doi-asserted-by":"crossref","unstructured":"Jin, L., He, J., May, J., & Ma, X. (2023). Challenges in context-aware neural machine translation. In Bouamor, H., Pino, J., and Bali, K., editors, Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 15246\u201315263, Singapore. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2023.emnlp-main.943"},{"key":"9854_CR32","doi-asserted-by":"crossref","unstructured":"Junczys-Dowmunt, M. (2019). Microsoft translator at WMT 2019: Towards large-scale document-level neural machine translation. In Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1), pp. 225\u2013233, Florence, Italy. Association for Computational Linguistics.","DOI":"10.18653\/v1\/W19-5321"},{"key":"9854_CR33","doi-asserted-by":"crossref","unstructured":"Junczys-Dowmunt, M. and Grundkiewicz, R. (2018). MS-UEdin submission to the WMT2018 APE shared task: Dual-source transformer for automatic post-editing. In Proceedings of the Third Conference on Machine Translation: Shared Task Papers, pp. 822\u2013826, Belgium, Brussels. Association for Computational Linguistics.","DOI":"10.18653\/v1\/W18-6467"},{"key":"9854_CR34","doi-asserted-by":"crossref","unstructured":"Junczys-Dowmunt, M., Grundkiewicz, R., Dwojak, T., Hoang, H., Heafield, K., Neckermann, T., Seide, F., Germann, U., Fikri\u00a0Aji, A., Bogoychev, N., Martins, A. F.\u00a0T., & Birch, A. (2018). Marian: Fast neural machine translation in C++. In Proceedings of ACL 2018, System Demonstrations, pp. 116\u2013121, Melbourne, Australia.","DOI":"10.18653\/v1\/P18-4020"},{"key":"9854_CR35","doi-asserted-by":"crossref","unstructured":"Kang, X., Zhao, Y., Zhang, J., & Zong, C. (2020). Dynamic context selection for document-level neural machine translation via reinforcement learning. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 2242\u20132254, Online. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2020.emnlp-main.175"},{"key":"9854_CR36","doi-asserted-by":"crossref","unstructured":"Karpinska, M. and Iyyer, M. (2023). Large language models effectively leverage document-level context for literary translation, but critical errors persist.","DOI":"10.18653\/v1\/2023.wmt-1.41"},{"key":"9854_CR37","doi-asserted-by":"crossref","unstructured":"Kim, Y., Tran, D.\u00a0T., & Ney, H. (2019). When and why is document-level context useful in neural machine translation? In Proceedings of the Fourth Workshop on Discourse in Machine Translation (DiscoMT 2019), pp. 24\u201334, Hong Kong, China. Association for Computational Linguistics.","DOI":"10.18653\/v1\/D19-6503"},{"key":"9854_CR38","unstructured":"Kimura, R., Iida, S., Cui, H., Hung, P.-H., Utsuro, T., & Nagata, M. (2019). Selecting informative context sentence by forced back-translation. In Proceedings of Machine Translation Summit XVII: Research Track, pp. 162\u2013171, Dublin, Ireland. European Association for Machine Translation."},{"key":"9854_CR39","unstructured":"Kingma, D.\u00a0P. and Ba, J. (2015). Adam: A method for stochastic optimization. In Proceedings of the 3rd International Conference on Learning Representations, San Diego, CA, USA."},{"key":"9854_CR40","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, Vancouver, Canada. Association for Computational Linguistics.","DOI":"10.18653\/v1\/P17-4012"},{"key":"9854_CR41","doi-asserted-by":"crossref","unstructured":"Kocmi, T., Avramidis, E., Bawden, R., Bojar, O., Dvorkovich, A., Federmann, C., Fishel, M., Freitag, M., Gowda, T., Grundkiewicz, R., Haddow, B., Karpinska, M., Koehn, P., Marie, B., Monz, C., Murray, K., Nagata, M., Popel, M., Popovi\u0107, M., Shmatova, M., Steingr\u00edmsson, S., & Zouhar, V. (2024). Findings of the WMT24 general machine translation shared task: The LLM era is here but MT is not solved yet. In Haddow, B., Kocmi, T., Koehn, P., and Monz, C., editors, Proceedings of the Ninth Conference on Machine Translation, pp. 1\u201346, Miami, Florida, USA. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2024.wmt-1.1"},{"key":"9854_CR42","unstructured":"Koehn, P. (2004). Statistical significance tests for machine translation evaluation. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp. 388\u2013395, Barcelona, Spain."},{"key":"9854_CR43","doi-asserted-by":"crossref","unstructured":"Koehn, P., Hoang, H., Birch, A., Callison-Burch, C., Federico, M., Bertoldi, N., Cowan, B., Shen, W., Moran, C., Zens, R., Dyer, C., Bojar, O., Constantin, A., & Herbst, E. (2007). Moses: Open source toolkit for statistical machine translation. In Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics, pp. 177\u2013180, Prague, Czech Republic.","DOI":"10.3115\/1557769.1557821"},{"key":"9854_CR44","doi-asserted-by":"crossref","unstructured":"L\u00e4ubli, S., Sennrich, R., & Volk, M. (2018). Has machine translation achieved human parity? a case for document-level evaluation. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 4791\u20134796, Brussels, Belgium. Association for Computational Linguistics.","DOI":"10.18653\/v1\/D18-1512"},{"key":"9854_CR45","doi-asserted-by":"crossref","unstructured":"Li, B., Liu, H., Wang, Z., Jiang, Y., Xiao, T., Zhu, J., Liu, T., & Li, C. (2020). Does multi-encoder help? a case study on context-aware neural machine translation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 3512\u20133518, Online. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2020.acl-main.322"},{"key":"9854_CR46","unstructured":"Lison, P. and Tiedemann, J. (2016). Opensubtitles2015: Extracting large parallel corpora from movie and tv subtitles. In International Conference on Language Resources and Evaluation."},{"key":"9854_CR47","unstructured":"Liu, S. and Zhang, X. (2020). Corpora for document-level neural machine translation. In Proceedings of the 12th Language Resources and Evaluation Conference, pp. 3775\u20133781, Marseille, France. European Language Resources Association."},{"key":"9854_CR48","unstructured":"Lopes, A., Farajian, M.\u00a0A., Bawden, R., Zhang, M., & Martins, A. F.\u00a0T. (2020). Document-level neural MT: A systematic comparison. In Proceedings of the 22nd Annual Conference of the European Association for Machine Translation, pp. 225\u2013234, Lisboa, Portugal. European Association for Machine Translation."},{"key":"9854_CR49","doi-asserted-by":"crossref","unstructured":"Mansimov, E., Melis, G., & Yu, L. (2021). Capturing document context inside sentence-level neural machine translation models with self-training. In Proceedings of the 2nd Workshop on Computational Approaches to Discourse, pp. 143\u2013153, Punta Cana, Dominican Republic and Online. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2021.codi-main.14"},{"key":"9854_CR50","doi-asserted-by":"crossref","unstructured":"Maruf, S. and Haffari, G. (2018). Document context neural machine translation with memory networks. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1275\u20131284, Melbourne, Australia. Association for Computational Linguistics.","DOI":"10.18653\/v1\/P18-1118"},{"key":"9854_CR51","doi-asserted-by":"crossref","unstructured":"Maruf, S., Martins, A. F.\u00a0T., & Haffari, G. (2019). Selective attention for context-aware neural machine translation. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 3092\u20133102, Minneapolis, Minnesota. Association for Computational Linguistics.","DOI":"10.18653\/v1\/N19-1313"},{"key":"9854_CR52","doi-asserted-by":"crossref","unstructured":"Miculicich, L., Ram, D., Pappas, N., & Henderson, J. (2018). Document-level neural machine translation with hierarchical attention networks. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 2947\u20132954, Brussels, Belgium. Association for Computational Linguistics.","DOI":"10.18653\/v1\/D18-1325"},{"key":"9854_CR53","doi-asserted-by":"crossref","unstructured":"Mitkov, R. (1999). Introduction: special issue on anaphora resolution in machine translation and multilingual nlp. Machine translation, pp. 159\u2013161.","DOI":"10.1023\/A:1011132522992"},{"key":"9854_CR54","doi-asserted-by":"crossref","unstructured":"M\u00fcller, M., Rios, A., Voita, E., & Sennrich, R. (2018). A large-scale test set for the evaluation of context-aware pronoun translation in neural machine translation. In Proceedings of the Third Conference on Machine Translation: Research Papers, pp. 61\u201372, Brussels, Belgium. Association for Computational Linguistics.","DOI":"10.18653\/v1\/W18-6307"},{"key":"9854_CR55","unstructured":"Nagata, M. and Morishita, M. (2020). A test set for discourse translation from Japanese to English. In Proceedings of the 12th Language Resources and Evaluation Conference, pp. 3704\u20133709, Marseille, France. European Language Resources Association."},{"key":"9854_CR56","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., & Zhu, W.-J. (2002). BLEU: A method for automatic evaluation of machine translation. In Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, pp. 311\u2013318, Philadelphia, Pennsylvania, USA.","DOI":"10.3115\/1073083.1073135"},{"key":"9854_CR57","doi-asserted-by":"crossref","unstructured":"Popovi\u0107, M. (2015). chrF: character n-gram F-score for automatic MT evaluation. In Proceedings of the Tenth Workshop on Statistical Machine Translation, pp. 392\u2013395, Lisbon, Portugal. Association for Computational Linguistics.","DOI":"10.18653\/v1\/W15-3049"},{"key":"9854_CR58","doi-asserted-by":"crossref","unstructured":"Post, M. (2018). A call for clarity in reporting BLEU scores. In Proceedings of the Third Conference on Machine Translation: Research Papers, pp. 186\u2013191, Brussels, Belgium.","DOI":"10.18653\/v1\/W18-6319"},{"key":"9854_CR59","unstructured":"Post, M. and Junczys-Dowmunt, M. (2023). Escaping the sentence-level paradigm in machine translation. Preprint at arXiv preprintarXiv:2304.12959v1."},{"key":"9854_CR60","doi-asserted-by":"crossref","unstructured":"Rei, R., Stewart, C., Farinha, A.\u00a0C., & Lavie, A. (2020). COMET: A neural framework for MT evaluation. In Webber, B., Cohn, T., He, Y., and Liu, Y., editors, Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 2685\u20132702, Online. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2020.emnlp-main.213"},{"key":"9854_CR61","doi-asserted-by":"crossref","unstructured":"Reimers, N. and Gurevych, I. (2020). Making monolingual sentence embeddings multilingual using knowledge distillation. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2020.emnlp-main.365"},{"key":"9854_CR62","unstructured":"Rikters, M. and Nakazawa, T. (2021). Revisiting context choices for context-aware machine translation. CoRR, abs\/2109.02995."},{"key":"9854_CR63","doi-asserted-by":"crossref","unstructured":"Rios\u00a0Gonzales, A., Mascarell, L., & Sennrich, R. (2017). Improving word sense disambiguation in neural machine translation with sense embeddings. In Proceedings of the Second Conference on Machine Translation, pp. 11\u201319, Copenhagen, Denmark. Association for Computational Linguistics.","DOI":"10.18653\/v1\/W17-4702"},{"key":"9854_CR64","unstructured":"Sarasola, I., Salaburu, P., & Landa, J. (2015). Hizkuntzen arteko corpusa (hac)."},{"key":"9854_CR65","doi-asserted-by":"crossref","unstructured":"Scherrer, Y., Tiedemann, J., & Lo\u00e1iciga, S. (2019). Analysing concatenation approaches to document-level NMT in two different domains. In Popescu-Belis, A., Lo\u00e1iciga, S., Hardmeier, C., and Xiong, D., editors, Proceedings of the Fourth Workshop on Discourse in Machine Translation (DiscoMT 2019), pp. 51\u201361, Hong Kong, China. Association for Computational Linguistics.","DOI":"10.18653\/v1\/D19-6506"},{"key":"9854_CR66","doi-asserted-by":"crossref","unstructured":"Sennrich, R. (2017). How grammatical is character-level neural machine translation? assessing MT quality with contrastive translation pairs. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pp. 376\u2013382, Valencia, Spain. Association for Computational Linguistics.","DOI":"10.18653\/v1\/E17-2060"},{"key":"9854_CR67","doi-asserted-by":"crossref","unstructured":"Sennrich, R., Haddow, B., & Birch, A. (2016). Neural machine translation of rare words with subword units. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1715\u20131725, Berlin, Germany. Association for Computational Linguistics.","DOI":"10.18653\/v1\/P16-1162"},{"key":"9854_CR68","doi-asserted-by":"crossref","unstructured":"Stojanovski, D., Krojer, B., Peskov, D., & Fraser, A. (2020). ContraCAT: Contrastive coreference analytical templates for machine translation. In Proceedings of the 28th International Conference on Computational Linguistics, pp. 4732\u20134749, Barcelona, Spain (Online). International Committee on Computational Linguistics.","DOI":"10.18653\/v1\/2020.coling-main.417"},{"key":"9854_CR69","doi-asserted-by":"crossref","unstructured":"Sugiyama, A. & Yoshinaga, N. (2019). Data augmentation using back-translation for context-aware neural machine translation. In Proceedings of the Fourth Workshop on Discourse in Machine Translation (DiscoMT 2019), pp. 35\u201344, Hong Kong, China. Association for Computational Linguistics.","DOI":"10.18653\/v1\/D19-6504"},{"key":"9854_CR70","unstructured":"Sun, Z., Wang, M., Zhou, H., Zhao, C., Huang, S., Chen, J., & Li, L. (2020). Capturing longer context for document-level neural machine translation: A multi-resolutional approach. CoRR, abs\/2010.08961."},{"key":"9854_CR71","doi-asserted-by":"publisher","first-page":"3537","DOI":"10.18653\/v1\/2022.findings-acl.279","volume-title":"Findings of the association for computational linguistics: ACL 2022","author":"Z Sun","year":"2022","unstructured":"Sun, Z., Wang, M., Zhou, H., Zhao, C., Huang, S., Chen, J., & Li, L. (2022). Rethinking document-level neural machine translation. Findings of the association for computational linguistics: ACL 2022 (pp. 3537\u20133548). Dublin."},{"key":"9854_CR72","doi-asserted-by":"crossref","unstructured":"Tan, X., Zhang, L., Xiong, D., & Zhou, G. (2019). Hierarchical modeling of global context for document-level neural machine translation. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 1576\u20131585, Hong Kong, China. Association for Computational Linguistics.","DOI":"10.18653\/v1\/D19-1168"},{"key":"9854_CR73","unstructured":"Tiedemann, J. (2010). Context adaptation in statistical machine translation using models with exponentially decaying cache. In Proceedings of the 2010 Workshop on Domain Adaptation for Natural Language Processing, pp. 8\u201315, Uppsala, Sweden. Association for Computational Linguistics."},{"key":"9854_CR74","unstructured":"Tiedemann, J. (2012). Parallel data, tools and interfaces in OPUS. In Proceedings of the 8th Language Resources and Evaluation Conference, pp. 2214\u20132218, Istanbul, Turkey."},{"key":"9854_CR75","doi-asserted-by":"crossref","unstructured":"Tiedemann, J. and Scherrer, Y. (2017). Neural machine translation with extended context. In Proceedings of the Third Workshop on Discourse in Machine Translation, pp. 82\u201392, Copenhagen, Denmark. Association for Computational Linguistics.","DOI":"10.18653\/v1\/W17-4811"},{"key":"9854_CR76","doi-asserted-by":"crossref","unstructured":"Toral, A., Castilho, S., Hu, K., & Way, A. (2018). Attaining the unattainable? reassessing claims of human parity in neural machine translation. In Proceedings of the Third Conference on Machine Translation: Research Papers, pp. 113\u2013123, Brussels, Belgium. Association for Computational Linguistics.","DOI":"10.18653\/v1\/W18-6312"},{"key":"9854_CR77","unstructured":"Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., Babaei, Y., Bashlykov, N., Batra, S., Bhargava, P., Bhosale, S., Bikel, D., Blecher, L., Canton Ferrer, C., Chen, M., Cucurull, G., Esiobu, D., Fernandes, J., Fu, J., Fu, W., \u2026 Scialom, T. (2023). Llama 2: Open foundation and fine-tuned chat models. Perprint at arXiv preprintarXiv:2307.09288."},{"key":"9854_CR78","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.\u00a0N., Kaiser, L., & Polosukhin, I. (2017). Attention is all you need. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA, pp. 5998\u20136008."},{"key":"9854_CR79","unstructured":"Vernikos, G., Thompson, B., Mathur, P., & Federico, M. (2022). Embarrassingly easy document-level MT metrics: How to convert any pretrained metric into a document-level metric. In Proceedings of the Seventh Conference on Machine Translation (WMT), pp. 118\u2013128, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics."},{"key":"9854_CR80","doi-asserted-by":"crossref","unstructured":"Voita, E., Sennrich, R., & Titov, I. (2019a). Context-aware monolingual repair for neural machine translation. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 877\u2013886, Hong Kong, China. Association for Computational Linguistics.","DOI":"10.18653\/v1\/D19-1081"},{"key":"9854_CR81","doi-asserted-by":"crossref","unstructured":"Voita, E., Sennrich, R., & Titov, I. (2019b). When a good translation is wrong in context: Context-aware machine translation improves on deixis, ellipsis, and lexical cohesion. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 1198\u20131212, Florence, Italy. Association for Computational Linguistics.","DOI":"10.18653\/v1\/P19-1116"},{"key":"9854_CR82","doi-asserted-by":"crossref","unstructured":"Voita, E., Serdyukov, P., Sennrich, R., & Titov, I. (2018). Context-aware neural machine translation learns anaphora resolution. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1264\u20131274, Melbourne, Australia. Association for Computational Linguistics.","DOI":"10.18653\/v1\/P18-1117"},{"key":"9854_CR83","doi-asserted-by":"crossref","unstructured":"Wang, L., Lyu, C., Ji, T., Zhang, Z., Yu, D., Shi, S., & Tu, Z. (2023). Document-level machine translation with large language models.","DOI":"10.18653\/v1\/2023.emnlp-main.1036"},{"key":"9854_CR84","doi-asserted-by":"crossref","unstructured":"Wang, L., Tu, Z., Way, A., & Liu, Q. (2017). Exploiting cross-sentence context for neural machine translation. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 2826\u20132831, Copenhagen, Denmark. Association for Computational Linguistics.","DOI":"10.18653\/v1\/D17-1301"},{"key":"9854_CR85","unstructured":"Webber, B. (2014). Discourse for machine translation. In Proceedings of the 28th Pacific Asia Conference on Language, Information and Computing, pp. 27\u201327, Phuket,Thailand. Department of Linguistics, Chulalongkorn University."},{"key":"9854_CR86","unstructured":"Wong, B. T.\u00a0M. and Kit, C. (2012). Extending machine translation evaluation metrics with lexical cohesion to document level. In Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pp. 1060\u20131068, Jeju Island, Korea. Association for Computational Linguistics."},{"issue":"3","key":"9854_CR87","doi-asserted-by":"publisher","first-page":"917","DOI":"10.1007\/s10994-021-06070-y","volume":"111","author":"X Wu","year":"2022","unstructured":"Wu, X., Xia, Y., Zhu, J., Wu, L., Xie, S., & Qin, T. (2022). A study of BERT for context-aware neural machine translation. Machine Learning, 111(3), 917\u2013935.","journal-title":"Machine Learning"},{"key":"9854_CR88","unstructured":"Xiao, T., Zhu, J., Yao, S., & Zhang, H. (2011). Document-level consistency verification in machine translation. In Proceedings of Machine Translation Summit XIII: Papers, Xiamen, China."},{"issue":"01","key":"9854_CR89","doi-asserted-by":"publisher","first-page":"7338","DOI":"10.1609\/aaai.v33i01.33017338","volume":"33","author":"H Xiong","year":"2019","unstructured":"Xiong, H., He, Z., Wu, H., & Wang, H. (2019). Modeling coherence for discourse neural machine translation. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 7338\u20137345.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"9854_CR90","doi-asserted-by":"crossref","unstructured":"Xu, M., Li, L., Wong, D.\u00a0F., Liu, Q., & Chao, L.\u00a0S. (2021). Document graph for neural machine translation. In Moens, M., Huang, X., Specia, L., and Yih, S.\u00a0W., editors, Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021, Virtual Event \/ Punta Cana, Dominican Republic, 7-11 November, 2021, pp. 8435\u20138448. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2021.emnlp-main.663"},{"key":"9854_CR91","doi-asserted-by":"crossref","unstructured":"Yamagishi, H. & Komachi, M. (2019). Improving context-aware neural machine translation with target-side context. CoRR, abs\/1909.00531.","DOI":"10.1007\/978-981-15-6168-9_10"},{"key":"9854_CR92","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1007\/978-3-031-30675-4_34","volume-title":"Database systems for advanced applications","author":"J Yang","year":"2023","unstructured":"Yang, J., Yin, Y., Ma, S., Yang, L., Guo, H., Huang, H., Zhang, D., Zeng, Y., Li, Z., & Wei, F. (2023). Hanoit: Enhancing context-aware translation via selective context. In X. Wang, M. L. Sapino, W.-S. Han, A. El Abbadi, G. Dobbie, Z. Feng, Y. Shao, & H. Yin (Eds.), Database systems for advanced applications (pp. 471\u2013486). Springer."},{"key":"9854_CR93","doi-asserted-by":"crossref","unstructured":"Yang, Z., Zhang, J., Meng, F., Gu, S., Feng, Y., & Zhou, J. (2019). Enhancing context modeling with a query-guided capsule network for document-level translation. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 1527\u20131537, Hong Kong, China. Association for Computational Linguistics.","DOI":"10.18653\/v1\/D19-1164"},{"key":"9854_CR94","doi-asserted-by":"publisher","first-page":"11939","DOI":"10.18653\/v1\/2024.findings-acl.710","volume":"2024","author":"X Zeng","year":"2024","unstructured":"Zeng, X., Liu, Y., Meng, F., & Zhou, J. (2024). Towards multiple references era-addressing data leakage and limited reference diversity in machine translation evaluation. In Findings of the Association for Computational Linguistics ACL, 2024, 11939\u201311951.","journal-title":"In Findings of the Association for Computational Linguistics ACL"},{"key":"9854_CR95","doi-asserted-by":"crossref","unstructured":"Zhang, J., Luan, H., Sun, M., Zhai, F., Xu, J., Zhang, M., & Liu, Y. (2018). Improving the transformer translation model with document-level context. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 533\u2013542, Brussels, Belgium. Association for Computational Linguistics.","DOI":"10.18653\/v1\/D18-1049"},{"key":"9854_CR96","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Yue, X., Huang, S., Chen, J., & Birch, A. (2020). Towards making the most of context in neural machine translation.","DOI":"10.24963\/ijcai.2020\/551"},{"key":"9854_CR97","first-page":"2765","volume":"2024","author":"W Zhu","year":"2024","unstructured":"Zhu, W., Liu, H., Dong, Q., Xu, J., Huang, S., Kong, L., Chen, J., & Li, L. (2024). Multilingual machine translation with large language models: Empirical results and analysis. In Findings of the Association for Computational Linguistics: NAACL, 2024, 2765\u20132781.","journal-title":"In Findings of the Association for Computational Linguistics: NAACL"}],"container-title":["Language Resources and Evaluation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10579-025-09854-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10579-025-09854-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10579-025-09854-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T05:16:42Z","timestamp":1765257402000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10579-025-09854-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,7]]},"references-count":97,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["9854"],"URL":"https:\/\/doi.org\/10.1007\/s10579-025-09854-z","relation":{},"ISSN":["1574-020X","1574-0218"],"issn-type":[{"type":"print","value":"1574-020X"},{"type":"electronic","value":"1574-0218"}],"subject":[],"published":{"date-parts":[[2025,8,7]]},"assertion":[{"value":"4 June 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 August 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no relevant financial or non-financial interests to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}