{"type":"ScholarlyArticle","title":"Correct-and-Memorize: Learning to Translate from Interactive Revisions","authors":[{"name":"Rongxiang Weng","slug":"rongxiang-weng","given":"Rongxiang","family":"Weng","affiliation":"National Key Laboratory for Novel Software Technology , Nanjing , China; Nanjing University , Nanjing , China"},{"name":"Hao Zhou","slug":"hao-zhou","given":"Hao","family":"Zhou","affiliation":"ByteDance AI Lab , Beijing , China"},{"name":"Shujian Huang","slug":"shujian-huang","given":"Shujian","family":"Huang","affiliation":"National Key Laboratory for Novel Software Technology , Nanjing , China; Nanjing University , Nanjing , China"},{"name":"Lei Li","slug":"lei-li","given":"Lei","family":"Li","affiliation":"ByteDance AI Lab , Beijing , China"},{"name":"Yifan Xia","slug":"yifan-xia","given":"Yifan","family":"Xia","affiliation":"National Key Laboratory for Novel Software Technology , Nanjing , China; Nanjing University , Nanjing , China"},{"name":"Jiajun Chen","slug":"jiajun-chen","given":"Jiajun","family":"Chen","affiliation":"National Key Laboratory for Novel Software Technology , Nanjing , China; Nanjing University , Nanjing , China"}],"abstract":"State-of-the-art machine translation models are still not on a par with human translators. Previous work takes human interactions into the neural machine translation process to obtain improved results in target languages. However, not all model--translation errors are equal -- some are critical while others are minor. In the meanwhile, same translation mistakes occur repeatedly in similar context. To solve both issues, we propose CAMIT, a novel method for translating in an interactive environment. Our proposed method works with critical revision instructions, therefore allows human to correct arbitrary words in model-translated sentences. In addition, CAMIT learns from and softly memorizes revision actions based on the context, alleviating the issue of repeating mistakes. Experiments in both ideal and real interactive translation settings demonstrate that our proposed CAMIT enhances machine translation results significantly while requires fewer revision instructions from human compared to previous methods.","doi":"10.24963/ijcai.2019/730","url":"https://ijcai.org/proceedings/2019/730","pdf":"https://ijcai.org/proceedings/2019/0730.pdf","markdown":"https://ijcai.org/proceedings/2019/730.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/730","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"Natural Language Processing","track":"Main track","number":730,"pages":{"first":5255,"last":5263},"keywords":["Natural Language Processing: Machine Translation","Humans and AI: Human-Computer Interaction","Natural Language Processing: Natural Language Generation"],"videos":[],"references":[{"position":1,"raw":"[Bahdanau et al., 2014] Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. Neural machine translation by jointly learning to align and translate. CoRR, 2014.","title":"Neural machine translation by jointly learning to align and translate","authors":"Dzmitry Bahdanau, Kyunghyun Cho, Yoshua Bengio","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Barrachina et al., 2009] Sergio Barrachina, Oliver Bender, Francisco Casacuberta, Jorge Civera, Elsa Cubel, Shahram Khadivi, Antonio Lagarda, Hermann Ney, Jesús Tomás, Enrique Vidal, et al. Statistical approaches to computer- assisted translation. CL, 2009.","title":"Statistical approaches to computerassisted translation","authors":"Sergio Barrachina, Oliver Bender, Francisco Casacuberta, Jorge Civera, Elsa Cubel, Shahram Khadivi, Antonio Lagarda, Hermann Ney, Jesús Tomás, Enrique Vidal","year":"2009","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Cettolo et al., 2012] Mauro Cettolo, Christian Girardi, and Marcello Federico. Wit 3 : Web inventory of transcribed and translated talks. 2012.","title":"Wit 3 : Web inventory of transcribed and translated talks","authors":"Mauro Cettolo, Christian Girardi, Marcello Federico","year":"2012","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Chen et al., 2018] Huadong Chen, Shujian Huang, David Chiang, Xinyu Dai, and Jiajun Chen. Combining char- acter and word information in neural machine translation using a multi-level attention. In NAACL, 2018.","title":"Combining character and word information in neural machine translation using a multi-level attention","authors":"Huadong Chen, Shujian Huang, David Chiang, Xinyu Dai, Jiajun Chen","year":"2018","venue":"NAACL","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Cheng et al., 2016] Shanbo Cheng, Shujian Huang, Huadong Chen, Xin-Yu Dai, and Jiajun Chen. Primt: A pick-revise framework for interactive machine translation. In NAACL, 2016.","title":"Primt: A pick-revise framework for interactive machine translation","authors":"Shanbo Cheng, Shujian Huang, Huadong Chen, Xin-Yu Dai, Jiajun Chen","year":"2016","venue":"NAACL","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Chiang, 2007] David Chiang. Hierarchical phrase-based translation. CL, 2007.","title":"Hierarchical phrase-based translation","authors":"David Chiang","year":"2007","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Cho et al., 2014] Kyunghyun Cho, Bart van Merrienboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. Learning phrase representations using rnn encoder-decoder for statistical machine translation. In EMNLP, 2014.","title":"Learning phrase representations using rnn encoder-decoder for statistical machine translation","authors":"Cho","year":"2014","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Dong et al., 2015] Daxiang Dong, Hua Wu, Wei He, Dian- hai Yu, and Haifeng Wang. Multi-task learning for multi- ple language translation. In ACL, 2015.","title":"Multi-task learning for multiple language translation","authors":"Daxiang Dong, Hua Wu, Wei He, Dianhai Yu, Haifeng Wang","year":"2015","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[González-Rubio et al., 2013] Jesús González-Rubio, Daniel Ortiz-Martínez, José-Miguel Benedí, and Fran- cisco Casacuberta. Interactive machine translation using hierarchical translation models. In EMNLP, 2013.","title":"Interactive machine translation using hierarchical translation models","authors":"González-Rubio","year":"2013","venue":"Jesús González","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Gu et al., 2016] Jiatao Gu, Zhengdong Lu, Hang Li, and Victor OK Li. Incorporating copying mechanism in sequence-to-sequence learning. arXiv, 2016.","title":"Incorporating copying mechanism in sequence-to-sequence learning","authors":"Gu","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Hasler et al., 2018] Eva Hasler, Adrià De Gispert, Gonzalo Iglesias, and Bill Byrne. Neural machine translation de- coding with terminology constraints. arXiv, 2018.","title":"Neural machine translation decoding with terminology constraints","authors":"Eva Hasler, Adrià De Gispert, Gonzalo Iglesias, Bill Byrne","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Hokamp and Liu, 2017] Chris Hokamp and Qun Liu. Lex- ically constrained decoding for sequence generation using grid beam search. In ACL, 2017.","title":"Lexically constrained decoding for sequence generation using grid beam search","authors":"Chris Hokamp, Qun Liu","year":"2017","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Kingma and Ba, 2014] Diederik P. Kingma and Jimmy Ba. Adam: A method for stochastic optimization. CoRR, 2014.","title":"Adam: A method for stochastic optimization","authors":"P Diederik, Jimmy Kingma, Ba","year":"2014","venue":"CoRR","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Knowles and Koehn, 2016] Rebecca Knowles and Philipp Koehn. Neural interactive translation prediction. AMTA, page 107, 2016.","title":"Neural interactive translation prediction","authors":"Rebecca Knowles, Philipp Koehn","year":"2016","venue":"AMTA","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Koehn et al., 2003] Philipp Koehn, Franz Josef Och, and Daniel Marcu. Statistical phrase-based translation. In NAACL, 2003.","title":"Statistical phrase-based translation","authors":"Philipp Koehn, Franz, Josef Och, Daniel Marcu","year":"2003","venue":"NAACL","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Langlais et al., 2000] Philippe Langlais, George Foster, and Guy Lapalme. Transtype: a computer-aided translation typing system. In NAACL, 2000.","title":"Transtype: a computer-aided translation typing system","authors":"Philippe Langlais, George Foster, Guy Lapalme","year":"2000","venue":"NAACL","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Liu et al., 2016] Lemao Liu, Masao Utiyama, Andrew Finch, and Eiichiro Sumita. Agreement on target- bidirectional neural machine translation. In NAACL, 2016.","title":"Agreement on targetbidirectional neural machine translation","authors":"Liu","year":"2016","venue":"NAACL","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Liu et al., 2018] D. Liu, J. Lv, F. He, and Y. Pu. BFGAN: Backward and Forward Generative Adversarial Networks for Lexically Constrained Sentence Generation. arXiv, 2018.","title":"BFGAN: Backward and Forward Generative Adversarial Networks for Lexically Constrained Sentence Generation","authors":"D Liu, J Lv, F He, Y Pu","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Luong et al., 2015a] Minh-Thang Luong, Quoc V. Le, Ilya Sutskever, Oriol Vinyals, and Lukasz Kaiser. Multi-task sequence to sequence learning. CoRR, 2015.","title":"Multi-task sequence to sequence learning","authors":"Luong","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Luong et al., 2015b] Minh-Thang Luong, Hieu Pham, and Christopher D. Manning. Effective approaches to attention-based neural machine translation. In EMNLP, 2015.","title":"Effective approaches to attention-based neural machine translation","authors":"Luong","year":"2015","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Mou et al., 2016] Lili Mou, Yiping Song, Rui Yan, Ge Li, Lu Zhang, and Zhi Jin. Sequence to backward and forward sequences: A content-introducing approach to generative short-text conversation. CoRR, 2016.","title":"Sequence to backward and forward sequences: A content-introducing approach to generative short-text conversation","authors":"Lili Mou, Yiping Song, Rui Yan, Ge Li, Lu Zhang, Zhi Jin","year":"2016","venue":"CoRR","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Papineni et al., 2002] Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. Bleu: A method for au- tomatic evaluation of machine translation. In ACL, 2002.","title":"Bleu: A method for automatic evaluation of machine translation","authors":"Kishore Papineni, Salim Roukos, Todd Ward, Wei-Jing Zhu","year":"2002","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Peris and Casacuberta, 2018] Á. Peris and F. Casacuberta. Active Learning for Interactive Neural Machine Transla- tion of Data Streams. CoRR, 2018.","title":"Active Learning for Interactive Neural Machine Translation of Data Streams","authors":"Casacuberta Peris, Á Peris, F Casacuberta","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Peris et al., 2017] Álvaro Peris, Luis Cebrián, and Fran- cisco Casacuberta. Online learning for neural machine translation post-editing. CoRR, 2017.","title":"Online learning for neural machine translation post-editing","authors":"Álvaro Peris, Luis Cebrián, Francisco Casacuberta","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Post and Vilar, 2018] Matt Post and David Vilar. Fast lexi- cally constrained decoding with dynamic beam allocation for neural machine translation. arXiv, 2018.","title":"Vilar. Fast lexically constrained decoding with dynamic beam allocation for neural machine translation","authors":"Vilar Post, Matt Post, David","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Sanchis-Trilles et al., 2014] Germán Sanchis-Trilles, Vi- cent Alabau, Christian Buck, Michael Carl, Francisco Casacuberta, Mercedes García-Martínez, Ulrich Germann, Jesús González-Rubio, Robin L Hill, Philipp Koehn, et al. Interactive translation prediction versus conventional post- editing in practice: a study with the casmacat workbench. MT, 2014.","title":"Interactive translation prediction versus conventional postediting in practice: a study with the casmacat workbench","authors":"Germán Sanchis-Trilles, Vicent Alabau, Christian Buck, Michael Carl, Francisco Casacuberta, Mercedes García-Martínez, Ulrich Germann, Jesús González-Rubio, Robin L Hill, Philipp Koehn","year":"2014","venue":"MT","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Sennrich et al., 2016] Rico Sennrich, Barry Haddow, and Alexandra Birch. Neural machine translation of rare words with subword units. In ACL, 2016.","title":"Neural machine translation of rare words with subword units","authors":"Sennrich","year":"2016","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Simard et al., 2007] Michel Simard, Nicola Ueffing, Pierre Isabelle, and Roland Kuhn. Rule-based translation with statistical phrase-based post-editing. In MT, 2007.","title":"Rule-based translation with statistical phrase-based post-editing","authors":"Michel Simard, Nicola Ueffing, Pierre Isabelle, Roland Kuhn","year":"2007","venue":null,"doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Sutskever et al., 2014] Ilya Sutskever, Oriol Vinyals, and Quoc V. Le. Sequence to sequence learning with neural networks. In In Proceedings of the NIPS. 2014.","title":"Quoc V. Le. Sequence to sequence learning with neural networks","authors":"Sutskever","year":"2014","venue":"Proceedings of the NIPS","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Tan et al., 2017] Yiming Tan, Zhiming Chen, Liu Huang, Lilin Zhang, Maoxi Li, and Mingwen Wang. Neural post- editing based on quality estimation. In MT, 2017.","title":"Neural postediting based on quality estimation","authors":"Yiming Tan, Zhiming Chen, Liu Huang, Lilin Zhang, Maoxi Li, Mingwen Wang","year":"2017","venue":"MT","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Tu et al., 2017] Zhaopeng Tu, Yang Liu, Shuming Shi, and Tong Zhang. Learning to remember translation history with a continuous cache. arXiv, 2017.","title":"Learning to remember translation history with a continuous cache","authors":"Tu","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Vaswani et al., 2017] Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. Attention is all you need. In NIPS, 2017.","title":"Attention is all you need","authors":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, Illia Polosukhin","year":"2017","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Weston et al., 2014] Jason Weston, Sumit Chopra, and An- toine Bordes. Memory networks. CoRR, 2014.","title":"Memory networks","authors":"Jason Weston, Sumit Chopra","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Wuebker et al., 2016] Joern Wuebker, Spence Green, John DeNero, Sasa Hasan, and Minh-Thang Luong. Models and inference for prefix-constrained machine translation. In ACL, 2016.","title":"Models and inference for prefix-constrained machine translation","authors":"Joern Wuebker, Spence Green, John Denero, Sasa Hasan, Minh-Thang Luong","year":"2016","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Yamada and Knight, 2001] Kenji Yamada and Kevin Knight. A syntax-based statistical translation model. In ACL, 2001.","title":"A syntax-based statistical translation model","authors":"Kenji Yamada, Kevin Knight","year":"2001","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Zheng et al., 2018] Zaixiang Zheng, Shujian Huang, Zewei Sun, Rongxiang Weng, Xin-Yu Dai, and Jiajun Chen. Learning to discriminate noises for incorporating external information in neural machine translation. In arXiv, 2018.","title":"Learning to discriminate noises for incorporating external information in neural machine translation","authors":"Zheng","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Álvaro Peris et al., 2016] Álvaro Peris, Miguel Domingo, and Francisco Casacuberta. Interactive neural machine translation. Computer Speech and Language, 2016.","title":"Álvaro Peris, Miguel Domingo, and Francisco Casacuberta","authors":"Álvaro Peris","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}