{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T10:01:38Z","timestamp":1766484098434,"version":"3.41.0"},"reference-count":34,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2017,9,15]],"date-time":"2017-09-15T00:00:00Z","timestamp":1505433600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"ICT Consilience Creative Program of MSIP\/IITP","award":["R0346-16-1007"],"award-info":[{"award-number":["R0346-16-1007"]}]},{"name":"ICT R8D Program of MSIP\/IITP","award":["R7119-16-1001"],"award-info":[{"award-number":["R7119-16-1001"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Asian Low-Resour. Lang. Inf. Process."],"published-print":{"date-parts":[[2018,3,31]]},"abstract":"<jats:p>\n            Recently, quality estimation has been attracting increasing interest from machine translation researchers, aiming at finding a good estimator for the \u201cquality\u201d of machine translation output. The common approach for quality estimation is to treat the problem as a supervised regression\/classification task using a quality-annotated noisy parallel corpus, called\n            <jats:italic>quality estimation data<\/jats:italic>\n            , as training data. However, the available size of quality estimation data remains small, due to the too-expensive cost of creating such data. In addition, most conventional quality estimation approaches rely on manually designed features to model nonlinear relationships between feature vectors and corresponding quality labels. To overcome these problems, this article proposes a novel neural network architecture for quality estimation task\u2014called the\n            <jats:italic>predictor-estimator<\/jats:italic>\n            \u2014that considers word prediction as an additional pre-task. The major component of the proposed neural architecture is a\n            <jats:italic>word prediction model<\/jats:italic>\n            based on a modified neural machine translation model\u2014a probabilistic model for predicting a target word conditioned on all the other source and target contexts. The underlying assumption is that the word prediction model is highly related to quality estimation models and is therefore able to transfer useful knowledge to quality estimation tasks. Our proposed quality estimation method sequentially trains the following two types of neural models: (1)\n            <jats:italic>Predictor<\/jats:italic>\n            :\n            <jats:italic>a neural word prediction model<\/jats:italic>\n            trained from parallel corpora and (2)\n            <jats:italic>Estimator<\/jats:italic>\n            :\n            <jats:italic>a neural quality estimation model<\/jats:italic>\n            trained from quality estimation data. To transfer word a prediction task to a quality estimation task, we generate\n            <jats:italic>quality estimation feature vectors<\/jats:italic>\n            from the word prediction model and feed them into the quality estimation model. The experimental results on WMT15 and 16 quality estimation datasets show that our proposed method has great potential in the various sub-challenges.\n          <\/jats:p>","DOI":"10.1145\/3109480","type":"journal-article","created":{"date-parts":[[2017,9,15]],"date-time":"2017-09-15T12:20:54Z","timestamp":1505478054000},"page":"1-22","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":22,"title":["Predictor-Estimator"],"prefix":"10.1145","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5990-8158","authenticated-orcid":false,"given":"Hyun","family":"Kim","sequence":"first","affiliation":[{"name":"Pohang University of Science and Technology (POSTECH), Pohang, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hun-Young","family":"Jung","sequence":"additional","affiliation":[{"name":"Pohang University of Science and Technology (POSTECH), Pohang, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongseok","family":"Kwon","sequence":"additional","affiliation":[{"name":"Pohang University of Science and Technology (POSTECH), Pohang, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jong-Hyeok","family":"Lee","sequence":"additional","affiliation":[{"name":"Pohang University of Science and Technology (POSTECH), Pohang, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seung-Hoon","family":"Na","sequence":"additional","affiliation":[{"name":"Chonbuk National University, Jeonju, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2017,9,15]]},"reference":[{"key":"e_1_2_1_1_1","first-page":"13","volume-title":"Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, 1044--1054","author":"Auli Michael","year":"2013"},{"volume-title":"ICLR","year":"2015","author":"Bahdanau Dzmitry","key":"e_1_2_1_2_1"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.3115\/1220355.1220401"},{"volume-title":"Findings of the 2014 workshop on statistical machine translation. In Proceedings of the 9th Workshop on Statistical Machine Translation. Association for Computational Linguistics, 12--58","year":"2014","author":"Bojar Ondrej","key":"e_1_2_1_4_1"},{"volume-title":"Findings of the 2016 conference on machine translation. In Proceedings of the 1st Conference on Machine Translation. Association for Computational Linguistics, 131--198","year":"2016","author":"Bojar Ond\u0159ej","key":"e_1_2_1_5_1"},{"volume-title":"Findings of the 2015 workshop on statistical machine translation. In Proceedings of the 10th Workshop on Statistical Machine Translation. Association for Computational Linguistics, 1--46","year":"2015","author":"Bojar Ond\u0159ej","key":"e_1_2_1_6_1"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"volume-title":"Natural language processing (almost) from scratch. J. Mach. Learn. Res. 12 (Nov","year":"2011","author":"Collobert Ronan","key":"e_1_2_1_8_1"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-1129"},{"volume-title":"Proceedings of the 7th Workshop on Statistical Machine Translation. Association for Computational Linguistics, 96--103","year":"2012","author":"Felice Mariano","key":"e_1_2_1_10_1"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10590-013-9139-3"},{"volume-title":"Proceedings of the 7th Workshop on Statistical Machine Translation. Association for Computational Linguistics, 104--108","year":"2012","author":"Gonz\u00e1lez-Rubio Jes\u00fas","key":"e_1_2_1_12_1"},{"volume-title":"Bidirectional LSTM Networks for Improved Phoneme Classification and Recognition","author":"Graves Alex","key":"e_1_2_1_13_1","doi-asserted-by":"crossref","DOI":"10.1007\/11550907_126"},{"key":"e_1_2_1_14_1","unstructured":"Tianxing He Yu Zhang Jasha Droppo and Kai Yu. 2016. On training bi-directional neural network language model with noise contrastive estimation. Retrieved from http:\/\/sigport.org\/1255.  Tianxing He Yu Zhang Jasha Droppo and Kai Yu. 2016. On training bi-directional neural network language model with noise contrastive estimation. Retrieved from http:\/\/sigport.org\/1255."},{"volume-title":"Bidirectional LSTM-CRF models for sequence tagging. CoRR abs\/1508.01991","year":"2015","author":"Huang Zhiheng","key":"e_1_2_1_15_1"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1059"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-2384"},{"volume-title":"Proceedings of the Korea Computer Congress (KCC\u201916)","year":"2016","author":"Kim Hyun","key":"e_1_2_1_18_1"},{"key":"e_1_2_1_19_1","first-page":"79","article-title":"Europarl: A parallel corpus for statistical machine translation","volume":"5","author":"Koehn Philipp","year":"2005","journal-title":"MT Summit"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-2385"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-3037"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-2387"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00056"},{"volume-title":"Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781","year":"2013","author":"Mikolov Tomas","key":"e_1_2_1_24_1"},{"volume-title":"Proceedings of the Sixth Workshop on Statistical Machine Translation. Association for Computational Linguistics, 198--206","year":"2011","author":"Niehues Jan","key":"e_1_2_1_25_1"},{"volume-title":"Proceedings of the 1st Conference on Machine Translation. Association for Computational Linguistics, 819--824","author":"Patel Raj Nath","key":"e_1_2_1_26_1"},{"volume-title":"Proceedings of the XIV Machine Translation Summit. 295--302","year":"2013","author":"Rubino Raphael","key":"e_1_2_1_27_1"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10590-014-9164-x"},{"volume-title":"Proceedings of the Association for Machine Translation in the Americas. 223--231","year":"2006","author":"Snover Matthew","key":"e_1_2_1_29_1"},{"volume-title":"Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, 612--621","year":"2010","author":"Soricut Radu","key":"e_1_2_1_30_1"},{"key":"e_1_2_1_31_1","unstructured":"Lucia Specia Varvara Logacheva and Carolina Scarton. 2016. WMT16 Quality Estimation Shared Task Training and Development Data. Retrieved from http:\/\/hdl.handle.net\/11372\/LRT-1646.  Lucia Specia Varvara Logacheva and Carolina Scarton. 2016. WMT16 Quality Estimation Shared Task Training and Development Data. Retrieved from http:\/\/hdl.handle.net\/11372\/LRT-1646."},{"volume-title":"Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics: System Demonstrations. Association for Computational Linguistics, 79--84","year":"2013","author":"Specia Lucia","key":"e_1_2_1_32_1"},{"volume-title":"Proceedings of the 13th Conference of the European Association for Machine Translation. 28--37","year":"2009","author":"Specia Lucia","key":"e_1_2_1_33_1"},{"volume-title":"ADADELTA: An adaptive learning rate method. arXiv preprint arXiv:1212.5701","year":"2012","author":"Zeiler Matthew D","key":"e_1_2_1_34_1"}],"container-title":["ACM Transactions on Asian and Low-Resource Language Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3109480","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3109480","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T02:13:44Z","timestamp":1750212824000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3109480"}},"subtitle":["Neural Quality Estimation Based on Target Word Prediction for Machine Translation"],"short-title":[],"issued":{"date-parts":[[2017,9,15]]},"references-count":34,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2018,3,31]]}},"alternative-id":["10.1145\/3109480"],"URL":"https:\/\/doi.org\/10.1145\/3109480","relation":{},"ISSN":["2375-4699","2375-4702"],"issn-type":[{"type":"print","value":"2375-4699"},{"type":"electronic","value":"2375-4702"}],"subject":[],"published":{"date-parts":[[2017,9,15]]},"assertion":[{"value":"2017-01-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2017-06-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2017-09-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}