{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T20:40:13Z","timestamp":1761597613384,"version":"3.41.0"},"reference-count":40,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2015,4,20]],"date-time":"2015-04-20T00:00:00Z","timestamp":1429488000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61303181"],"award-info":[{"award-number":["61303181"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"High New Technology Research and Development Program of Xinjiang Uyghur Autonomous Region","award":["201312103"],"award-info":[{"award-number":["201312103"]}]},{"name":"International Science & Technology Cooperation Program of China","award":["2014DFA11350"],"award-info":[{"award-number":["2014DFA11350"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Asian Low-Resour. Lang. Inf. Process."],"published-print":{"date-parts":[[2015,4,20]]},"abstract":"<jats:p>Measuring the quality of the translation rules and their composition is an essential issue in the conventional statistical machine translation (SMT) framework. To express the translation quality, the previous lexical and phrasal probabilities are calculated only according to the co-occurrence statistics in the bilingual corpus and may be not reliable due to the data sparseness problem. To address this issue, we propose measuring the quality of the translation rules and their composition in the semantic vector embedding space (VES). We present a recursive neural network (RNN)-based translation framework, which includes two submodels. One is the bilingually-constrained recursive auto-encoder, which is proposed to convert the lexical translation rules into compact real-valued vectors in the semantic VES. The other is a type-dependent recursive neural network, which is proposed to perform the decoding process by minimizing the semantic gap (meaning distance) between the source language string and its translation candidates at each state in a bottom-up structure. The RNN-based translation model is trained using a max-margin objective function that maximizes the margin between the reference translation and the n-best translations in forced decoding. In the experiments, we first show that the proposed vector representations for the translation rules are very reliable for application in translation modeling. We further show that the proposed type-dependent, RNN-based model can significantly improve the translation quality in the large-scale, end-to-end Chinese-to-English translation evaluation.<\/jats:p>","DOI":"10.1145\/2699927","type":"journal-article","created":{"date-parts":[[2015,6,18]],"date-time":"2015-06-18T18:14:05Z","timestamp":1434651245000},"page":"1-26","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Towards Machine Translation in Semantic Vector Space"],"prefix":"10.1145","volume":"14","author":[{"given":"Jiajun","family":"Zhang","sequence":"first","affiliation":[{"name":"Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shujie","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mu","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Zhou","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengqing","family":"Zong","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2015,4,20]]},"reference":[{"volume-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing. 1044--1054","year":"2013","author":"Auli Michael","key":"e_1_2_1_1_1"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.5555\/944919.944966"},{"volume-title":"Innovations in Machine Learning. Studies in Fuzziness and Soft Computing","author":"Bengio Yoshua","key":"e_1_2_1_3_1"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1162\/coli.2007.33.2.201"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390177"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2078186"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-1129"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2021068"},{"volume-title":"Proceedings of the Machine Translation Summit XI.","year":"2007","author":"Eck Matthias","key":"e_1_2_1_9_1"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.3115\/1220175.1220296"},{"volume-title":"Proceedings of the 52nd ACL. 699--709","year":"2014","author":"Gao Jianfeng","key":"e_1_2_1_11_1"},{"volume-title":"Proceedings of EMNLP.","year":"2007","author":"Johnson John Howard","key":"e_1_2_1_12_1"},{"volume-title":"Proceedings of AMTA. 66--73","year":"2006","author":"Huang Liang","key":"e_1_2_1_13_1"},{"volume-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing. 1700--1709","year":"2013","author":"Kalchbrenner Nal","key":"e_1_2_1_14_1"},{"volume-title":"Proceedings of EMNLP. 388--395","year":"2004","author":"Koehn Philipp","key":"e_1_2_1_15_1"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.5555\/1557769.1557821"},{"volume-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing.","year":"2013","author":"Li Peng","key":"e_1_2_1_17_1"},{"volume-title":"Proceedings of the Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning. 962--971","year":"2012","author":"Ling Wang","key":"e_1_2_1_18_1"},{"volume-title":"Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics. 791--801","year":"2013","author":"Liu Lemao","key":"e_1_2_1_19_1"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.3115\/1220175.1220252"},{"key":"e_1_2_1_21_1","unstructured":"Tomas Mikolov. 2012. Statistical language models based on neural networks. Ph.D Dissertation. Brno University of Technology.  Tomas Mikolov. 2012. Statistical language models based on neural networks. Ph.D Dissertation. Brno University of Technology."},{"volume-title":"Proceedings of NIPS.","year":"2013","author":"Mikolov Tomas","key":"e_1_2_1_22_1"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073133"},{"volume-title":"Proceedings of the International Conference on Artificial Intelligence and Statistics. 380--387","year":"2007","author":"Ratliff Nathan D.","key":"e_1_2_1_24_1"},{"key":"e_1_2_1_25_1","first-page":"137","article-title":"Continuous-space language models for statistical machine translation","volume":"93","author":"Schwenk Holger","year":"2010","journal-title":"Prague Bullet. Math. Linguistics"},{"volume-title":"Proceedings of the 24th COLING. 1071--1080","year":"2012","author":"Schwenk Holger","key":"e_1_2_1_26_1"},{"volume-title":"Proceedings of ACL.","author":"Socher Richard","key":"e_1_2_1_27_1"},{"volume-title":"Proceedings of the NIPS-2010 Deep Learning and Unsupervised Feature Learning Workshop.","author":"Socher Richard","key":"e_1_2_1_28_1"},{"volume-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing. 151--161","author":"Socher Richard","key":"e_1_2_1_29_1"},{"volume-title":"Proceedings of Summit XII. 144--151","year":"2009","author":"Tomeh Nadi","key":"e_1_2_1_30_1"},{"volume-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing. 1387--1392","year":"2013","author":"Vaswani Ashish","key":"e_1_2_1_31_1"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.5555\/972705.972707"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.3115\/1220175.1220241"},{"volume-title":"Proceedings of the Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning. 972--983","year":"2012","author":"Zens Richard","key":"e_1_2_1_34_1"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-1011"},{"volume-title":"Proceedings of the 28th AAAI.","year":"2014","author":"Zhang Jiajun","key":"e_1_2_1_36_1"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.5555\/2145432.2145456"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2255283"},{"volume-title":"Proceedings of the Annual Meeting of the Association of Computational Linguistics (ACL). 559--567","year":"2008","author":"Zhang Min","key":"e_1_2_1_39_1"},{"volume-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing. 1393--1398","author":"Zou Will Y.","key":"e_1_2_1_40_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\/2699927","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2699927","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T06:16:59Z","timestamp":1750227419000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2699927"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,4,20]]},"references-count":40,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2015,4,20]]}},"alternative-id":["10.1145\/2699927"],"URL":"https:\/\/doi.org\/10.1145\/2699927","relation":{},"ISSN":["2375-4699","2375-4702"],"issn-type":[{"type":"print","value":"2375-4699"},{"type":"electronic","value":"2375-4702"}],"subject":[],"published":{"date-parts":[[2015,4,20]]},"assertion":[{"value":"2014-04-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2014-10-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2015-04-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}