{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T16:41:48Z","timestamp":1778776908143,"version":"3.51.4"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2021,3,30]],"date-time":"2021-03-30T00:00:00Z","timestamp":1617062400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,3,30]],"date-time":"2021-03-30T00:00:00Z","timestamp":1617062400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"name":"Digital Economy Promotion Agency Thailand","award":["MP-62-003"],"award-info":[{"award-number":["MP-62-003"]}]},{"DOI":"10.13039\/501100004396","name":"Thailand Research Fund","doi-asserted-by":"publisher","award":["MRG6280175"],"award-info":[{"award-number":["MRG6280175"]}],"id":[{"id":"10.13039\/501100004396","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002873","name":"Chulalongkorn University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002873","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Siam Commercial Bank"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Lang Resources & Evaluation"],"published-print":{"date-parts":[[2022,6]]},"DOI":"10.1007\/s10579-021-09536-6","type":"journal-article","created":{"date-parts":[[2021,3,30]],"date-time":"2021-03-30T17:03:01Z","timestamp":1617123781000},"page":"477-499","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["A large English\u2013Thai parallel corpus from the web and machine-generated text"],"prefix":"10.1007","volume":"56","author":[{"given":"Lalita","family":"Lowphansirikul","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Charin","family":"Polpanumas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2270-6082","authenticated-orcid":false,"given":"Attapol T.","family":"Rutherford","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sarana","family":"Nutanong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,3,30]]},"reference":[{"key":"9536_CR1","unstructured":"Abdelali, A., Guzman, F., Sajjad, H., & Vogel, S. (2014). The AMARA corpus: Building parallel language resources for the educational domain. In: Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC\u201914), European Language Resources Association (ELRA), Reykjavik, Iceland, pp 1856\u20131862, http:\/\/www.lrec-conf.org\/proceedings\/lrec2014\/pdf\/877_Paper.pdf"},{"key":"9536_CR2","doi-asserted-by":"publisher","unstructured":"Agi\u0107 \u017d, V. I. (2019). JW300: A wide-coverage parallel corpus for low-resource languages. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Association for Computational Linguistics, Florence, Italy, pp 3204\u20133210. https:\/\/doi.org\/10.18653\/v1\/P19-1310, https:\/\/www.aclweb.org\/anthology\/P19-1310","DOI":"10.18653\/v1\/P19-1310"},{"key":"9536_CR3","unstructured":"Bahdanau, D., Cho, K., & Bengio, Y. (2014). Neural machine translation by jointly learning to align and translate. ArXiv 1409"},{"key":"9536_CR4","doi-asserted-by":"crossref","unstructured":"Byrne, B., Krishnamoorthi, K., Sankar, C., Neelakantan, A., Duckworth, D., Yavuz, S., Goodrich, B., Dubey, A., Cedilnik, A., & Kim, KY. (2019). Taskmaster-1: Toward a realistic and diverse dialog dataset. arXiv preprint arXiv:190905358","DOI":"10.18653\/v1\/D19-1459"},{"key":"9536_CR5","unstructured":"Cettolo, M., Niehues, J., St\u00fcker, S., Bentivogli, L., Cattoni, R., & Federico, M. (2015). The iwslt 2015 evaluation campaign"},{"key":"9536_CR6","doi-asserted-by":"publisher","unstructured":"Chaudhary, V., Tang, Y., Guzm\u00e1n, F., Schwenk, H., & Koehn, P. (2019). Low-resource corpus filtering using multilingual sentence embeddings. In: Proceedings of the Fourth Conference on Machine Translation (Vol. 3: Shared Task Papers, Day 2), Association for Computational Linguistics, Florence, Italy, pp 261\u2013266, https:\/\/doi.org\/10.18653\/v1\/W19-5435, https:\/\/www.aclweb.org\/anthology\/W19-5435","DOI":"10.18653\/v1\/W19-5435"},{"key":"9536_CR7","doi-asserted-by":"publisher","unstructured":"Chen, T., & Kan, M. Y. (2011). Creating a live, public short message service corpus: The nus sms corpus. Language Resources and Evaluation. https:\/\/doi.org\/10.1007\/s10579-012-9197-9.","DOI":"10.1007\/s10579-012-9197-9"},{"issue":"2","key":"9536_CR8","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1007\/s10579-014-9287-y","volume":"49","author":"C Christodouloupoulos","year":"2015","unstructured":"Christodouloupoulos, C., & Steedman, M. (2015). A massively parallel corpus: The bible in 100 languages. Language Resources and Evaluation, 49(2), 375\u2013395. https:\/\/doi.org\/10.1007\/s10579-014-9287-y.","journal-title":"Language Resources and Evaluation"},{"key":"9536_CR9","unstructured":"Dolan, W. B., & Brockett, C. (2005). Automatically constructing a corpus of sentential paraphrases. In: Proceedings of the Third International Workshop on Paraphrasing (IWP2005), https:\/\/www.aclweb.org\/anthology\/I05-5002"},{"key":"9536_CR10","unstructured":"Espl\u00e0, M., & Transducens, G. (2009). Bitextor, a free\/open-source software to harvest translation memories from multilingual websites"},{"key":"9536_CR11","unstructured":"Espl\u00e0, M., Forcada, M., Ram\u00edrez-S\u00e1nchez, G., & Hoang, H. (2019). ParaCrawl: Web-scale parallel corpora for the languages of the EU. In: Proceedings of Machine Translation Summit XVII Volume 2: Translator, Project and User Tracks, European Association for Machine Translation, Dublin, Ireland, pp 118\u2013119, https:\/\/www.aclweb.org\/anthology\/W19-6721"},{"key":"9536_CR12","unstructured":"Espl\u00e0-Gomis, M., & Forcada, ML. (2009). Bitextor, a free\/open-source software to harvest translation memories from multilingual websites. Proceedings of MT Summit XII, Ottawa, Canada Association for Machine Translation in the Americas"},{"issue":"1","key":"9536_CR13","first-page":"75","volume":"19","author":"WA Gale","year":"1993","unstructured":"Gale, W. A., & Church, K. (1993). A program for aligning sentences in bilingual corpora. Computational Linguistics, 19(1), 75\u2013102.","journal-title":"Computational Linguistics"},{"key":"9536_CR14","unstructured":"Gehring, J., Auli, M., Grangier, D., Yarats, D., & Dauphin, Y. N. (2017). Convolutional sequence to sequence learning. CoRR arXiv:abs\/1705.03122,"},{"key":"9536_CR15","unstructured":"Hassan, H., Aue, A., Chen, C., Chowdhary, V., Clark, J., Federmann, C., Huang, X., Junczys-Dowmunt, M., Lewis, W., Li, M., Liu, S., Liu, T. Y., Luo, R., Menezes, A., Qin, T., Seide, F., Tan, X., Tian, F., Wu, L., Wu, S., Xia, Y., Zhang, D., Zhang, Z., & Zhou, M. (2018). Achieving human parity on automatic chinese to english news translation. ArXiv abs\/1803.05567"},{"key":"9536_CR16","unstructured":"Keskar, N. S., McCann, B., Varshney, L. R., Xiong, C., & Socher, R. (2019). Ctrl: A conditional transformer language model for controllable generation. arXiv:1909.05858"},{"key":"9536_CR17","first-page":"79","volume":"5","author":"P Koehn","year":"2005","unstructured":"Koehn, P. (2005). Europarl: A parallel corpus for statistical machine translation. MT Summit Citeseer, 5, 79\u201386.","journal-title":"MT Summit Citeseer"},{"key":"9536_CR18","doi-asserted-by":"publisher","unstructured":"Koehn, P., & Knowles, R. (2017). Six challenges for neural machine translation. In: Proceedings of the First Workshop on Neural Machine Translation, Association for Computational Linguistics, Vancouver, pp 28\u201339. https:\/\/doi.org\/10.18653\/v1\/W17-3204, https:\/\/www.aclweb.org\/anthology\/W17-3204","DOI":"10.18653\/v1\/W17-3204"},{"key":"9536_CR19","doi-asserted-by":"publisher","unstructured":"Kosawat, K., Boriboon, M., Chootrakool, P., Chotimongkol, A., Klaithin, S., Kongyoung, S., Kriengket, K., Phaholphinyo, S., Purodakananda, S., Thanakulwarapas, T., & Wutiwiwatchai, C. (2009). Best 2009 : Thai word segmentation software contest. In: 2009 Eighth International Symposium on Natural Language Processing, pp 83\u201388. https:\/\/doi.org\/10.1109\/SNLP.2009.5340941","DOI":"10.1109\/SNLP.2009.5340941"},{"key":"9536_CR20","doi-asserted-by":"publisher","unstructured":"Kudo, T., & Richardson, J. (2018). SentencePiece: A simple and language independent subword tokenizer and detokenizer for neural text processing. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, Association for Computational Linguistics, Brussels, Belgium, pp 66\u201371, https:\/\/doi.org\/10.18653\/v1\/D18-2012, https:\/\/www.aclweb.org\/anthology\/D18-2012","DOI":"10.18653\/v1\/D18-2012"},{"key":"9536_CR21","unstructured":"Lison, P., & Tiedemann, J. (2016). OpenSubtitles2016: Extracting large parallel corpora from movie and TV subtitles. In: Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC\u201916), European Language Resources Association (ELRA), Portoro\u017e, Slovenia, pp 923\u2013929, https:\/\/www.aclweb.org\/anthology\/L16-1147"},{"key":"9536_CR22","doi-asserted-by":"publisher","unstructured":"Loper, E., & Bird, S. (2002). Nltk: The natural language toolkit. In: Proceedings of the ACL-02 Workshop on Effective Tools and Methodologies for Teaching Natural Language Processing and Computational Linguistics, Vol. 1, Association for Computational Linguistics, USA, ETMTNLP\u201902, p 63\u201370, https:\/\/doi.org\/10.3115\/1118108.1118117","DOI":"10.3115\/1118108.1118117"},{"key":"9536_CR23","unstructured":"Ma, X. (2006). Champollion: A robust parallel text sentence aligner. In: LREC, pp 489\u2013492"},{"key":"9536_CR24","doi-asserted-by":"crossref","unstructured":"Ott, M., Edunov, S., Grangier, D., & Auli, M. (2018). Scaling neural machine translation. ArXiv abs\/1806.00187","DOI":"10.18653\/v1\/W18-6301"},{"key":"9536_CR25","doi-asserted-by":"crossref","unstructured":"Ott, M., Edunov, S., Baevski, A., Fan, A., Gross, S., Ng, N., Grangier, D., & Auli, M. (2019). fairseq: A fast, extensible toolkit for sequence modeling. In: Proceedings of NAACL-HLT 2019: Demonstrations","DOI":"10.18653\/v1\/N19-4009"},{"key":"9536_CR26","doi-asserted-by":"publisher","unstructured":"Papineni, K., Roukos, S., Ward, T., & Zhu, WJ. (2002). Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, Association for Computational Linguistics, Philadelphia, Pennsylvania, USA, pp 311\u2013318, https:\/\/doi.org\/10.3115\/1073083.1073135, https:\/\/www.aclweb.org\/anthology\/P02-1040","DOI":"10.3115\/1073083.1073135"},{"key":"9536_CR27","doi-asserted-by":"publisher","unstructured":"Phatthiyaphaibun, W., Chaovavanich, K., Polpanumas, C., Suriyawongkul, A., Lowphansirikul, L., & Chormai, P. (2020). Pythainlp\/pythainlp: Pythainlp 2.1.4. https:\/\/doi.org\/10.5281\/zenodo.3659277.","DOI":"10.5281\/zenodo.3659277"},{"key":"9536_CR28","doi-asserted-by":"publisher","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, Association for Computational Linguistics, Lisbon, Portugal, pp 392\u2013395, https:\/\/doi.org\/10.18653\/v1\/W15-3049, https:\/\/www.aclweb.org\/anthology\/W15-3049","DOI":"10.18653\/v1\/W15-3049"},{"key":"9536_CR29","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, Association for Computational Linguistics, Belgium, Brussels, pp 186\u2013191, https:\/\/www.aclweb.org\/anthology\/W18-6319","DOI":"10.18653\/v1\/W18-6319"},{"key":"9536_CR30","unstructured":"Slayden, G., Hwang, M. Y., & Schwartz, L. (2010). Thai sentence-breaking for large-scale smt. In: Proceedings of the 1st Workshop on South and Southeast Asian Natural Language Processing, pp. 8\u201316"},{"key":"9536_CR31","unstructured":"Sornlertlamvanich, V., Charoenporn, T., & Isahara, H. (1997). Orchid: Thai part-of-speech tagged corpus. National Electronics and Computer Technology Center Technical Report pp. 5\u201319"},{"key":"9536_CR32","doi-asserted-by":"crossref","unstructured":"Tangsirirat, N., Suchato, A., Punyabukkana, P., & Wutiwiwatchai, C. (2013). Contextual behaviour features and grammar rules for thai sentence-breaking. 2013 10th International Conference on Electrical Engineering\/Electronics (pp. 1\u20134). Telecommunications and Information Technology, IEEE: Computer.","DOI":"10.1109\/ECTICon.2013.6559581"},{"key":"9536_CR33","doi-asserted-by":"publisher","unstructured":"Thompson, B., & Koehn, P. (2019). Vecalign: Improved sentence alignment in linear time and space. 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), Association for Computational Linguistics, Hong Kong, China, pp. 1342\u20131348, https:\/\/doi.org\/10.18653\/v1\/D19-1136, https:\/\/www.aclweb.org\/anthology\/D19-1136","DOI":"10.18653\/v1\/D19-1136"},{"key":"9536_CR34","unstructured":"Tiedemann, J. (2012). Parallel data, tools and interfaces in OPUS. In: Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC\u201912), European Language Resources Association (ELRA), Istanbul, Turkey, pp. 2214\u20132218, http:\/\/www.lrec-conf.org\/proceedings\/lrec2012\/pdf\/463_Paper.pdf"},{"issue":"292","key":"9536_CR35","first-page":"247","volume":"4","author":"D Varga","year":"2007","unstructured":"Varga, D., Hal\u00e1csy, P., Kornai, A., Nagy, V., N\u00e9meth, L., & Tr\u00f3n, V. (2007). Parallel corpora for medium density languages. Amsterdam Studies In The Theory And History Of Linguistic Science Series, 4(292), 247.","journal-title":"Amsterdam Studies In The Theory And History Of Linguistic Science Series"},{"key":"9536_CR36","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, AN., Kaiser, L., Polosukhin, I. (2017). Attention is all you need. CoRR arXiv:abs\/1706.03762"},{"key":"9536_CR37","doi-asserted-by":"crossref","unstructured":"Yang, Y., Cer, D. M., Ahmad, A., Guo, M., Law, J., Constant, N., \u00c1brego, G. H., Yuan, S., Tar, C., Sung, YH., Strope, B., & Kurzweil, R. (2019). Multilingual universal sentence encoder for semantic retrieval. ArXiv:abs\/1907.04307","DOI":"10.18653\/v1\/2020.acl-demos.12"},{"key":"9536_CR38","unstructured":"Zaidan, O. (2012). Crowdsourcing annotation for machine learning in natural language processing tasks"},{"key":"9536_CR39","unstructured":"Ziemski, M., Junczys-Dowmunt, M., & Pouliquen, B. (2016). The united nations parallel corpus v1.0. In: Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC\u201916), European Language Resources Association (ELRA), Portoro\u017e, Slovenia, pp. 3530\u20133534, https:\/\/www.aclweb.org\/anthology\/L16-1561"}],"container-title":["Language Resources and Evaluation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10579-021-09536-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10579-021-09536-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10579-021-09536-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,11]],"date-time":"2022-06-11T10:09:32Z","timestamp":1654942172000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10579-021-09536-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3,30]]},"references-count":39,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2022,6]]}},"alternative-id":["9536"],"URL":"https:\/\/doi.org\/10.1007\/s10579-021-09536-6","relation":{},"ISSN":["1574-020X","1574-0218"],"issn-type":[{"value":"1574-020X","type":"print"},{"value":"1574-0218","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,3,30]]},"assertion":[{"value":"2 March 2021","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 March 2021","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}