{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,3,29]],"date-time":"2022-03-29T04:09:24Z","timestamp":1648526964759},"reference-count":48,"publisher":"MIT Press - Journals","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Transactions of the Association for Computational Linguistics"],"published-print":{"date-parts":[[2019,11]]},"abstract":"<jats:p> In many machine learning scenarios, supervision by gold labels is not available and conse quently neural models cannot be trained directly by maximum likelihood estimation. In a weak supervision scenario, metric-augmented objectives can be employed to assign feedback to model outputs, which can be used to extract a supervision signal for training. We present several objectives for two separate weakly supervised tasks, machine translation and semantic parsing. We show that objectives should actively discourage negative outputs in addition to promoting a surrogate gold structure. This notion of bipolarity is naturally present in ramp loss objectives, which we adapt to neural models. We show that bipolar ramp loss objectives outperform other non-bipolar ramp loss objectives and minimum risk training on both weakly supervised tasks, as well as on a supervised machine translation task. Additionally, we introduce a novel token-level ramp loss objective, which is able to outperform even the best sequence-level ramp loss on both weakly supervised tasks. <\/jats:p>","DOI":"10.1162\/tacl_a_00265","type":"journal-article","created":{"date-parts":[[2019,5,29]],"date-time":"2019-05-29T17:06:41Z","timestamp":1559149601000},"page":"233-248","source":"Crossref","is-referenced-by-count":0,"title":["Learning Neural Sequence-to-Sequence Models from Weak Feedback with Bipolar Ramp Loss"],"prefix":"10.1162","volume":"7","author":[{"given":"Laura","family":"Jehl","sequence":"first","affiliation":[{"name":"Computational Linguistics, Heidelberg University, 69120 Heidelberg, Germany."}]},{"given":"Carolin","family":"Lawrence","sequence":"additional","affiliation":[{"name":"Computational Linguistics, Heidelberg University, 69120 Heidelberg, Germany."}]},{"given":"Stefan","family":"Riezler","sequence":"additional","affiliation":[{"name":"Computational Linguistics & IWR, Heidelberg University, 69120 Heidelberg, Germany."}]}],"member":"281","reference":[{"key":"bib1","volume-title":"International Conference on Learning Representations (ICLR)","author":"Bahdanau Dzmitry","year":"2015"},{"key":"bib2","volume-title":"Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Bentivogli Luisa","year":"2016"},{"key":"bib3","volume-title":"Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Berant Jonathan","year":"2013"},{"key":"bib4","volume-title":"Proceedings of the 16th Conference of the European Association for Machine Translation (EAMT)","author":"Cettolo Mauro","year":"2012"},{"key":"bib5","volume-title":"Advances in Neural Information Processing Systems (NIPS)","author":"Chapelle Olivier","year":"2009"},{"key":"bib6","volume-title":"Proceedings of the 9th Workshop on Statistical Machine Translation","author":"Chen Boxing","year":"2014"},{"issue":"1","key":"bib7","first-page":"1159","volume":"13","author":"Chiang David","year":"2012","journal-title":"Journal of Machine Learning Research"},{"key":"bib8","volume-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Cho Kyunghyun","year":"2014"},{"key":"bib9","volume-title":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Choi Eunsol","year":"2017"},{"key":"bib10","volume-title":"Proceedings of the 2011 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (HLT-NAACL)","author":"Clark Jonathan H.","year":"2011"},{"key":"bib11","volume-title":"Proceedings of the 14th Conference on Computational Natural Language Learning","author":"Clarke James","year":"2010"},{"key":"bib12","volume-title":"Proceedings of the 2002 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Collins Michael","year":"2002"},{"key":"bib13","volume-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Duong Long","year":"2018"},{"key":"bib14","volume-title":"Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (HLT-NAACL)","author":"Edunov Sergey","year":"2018"},{"key":"bib15","volume-title":"Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC)","author":"Eisele Andreas","year":"2010"},{"key":"bib16","volume-title":"Proceedings of the 34th International Conference on Machine Learning (ICML)","author":"Gehring Jonas","year":"2017"},{"key":"bib17","volume-title":"Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (HLT-NAACL)","author":"Gimpel Kevin","year":"2012"},{"key":"bib18","first-page":"1471","volume":"5","author":"Greensmith Evan","year":"2004","journal-title":"Journal of Machine Learning Research"},{"key":"bib19","volume-title":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Guu Kelvin","year":"2017"},{"key":"bib20","volume-title":"Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (HLT-NAACL)","author":"Haas Carolin","year":"2016"},{"key":"bib21","volume-title":"Advances in Neural Information Processing Systems (NIPS)","author":"Hazan Tamir","year":"2010"},{"key":"bib22","volume-title":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Iyyer Mohit","year":"2017"},{"key":"bib23","volume-title":"Proceedings of the 26th International Conference on Computational Linguistics (COLING)","author":"Jehl Laura","year":"2016"},{"key":"bib24","volume-title":"Proceedings of the Machine Translation Summit","volume":"5","author":"Koehn Philipp","year":"2005"},{"key":"bib25","volume-title":"Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Ko\u010disk\u00fd Tom\u00e1\u0161","year":"2016"},{"key":"bib26","volume-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Lawrence Carolin","year":"2018"},{"key":"bib27","volume-title":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Liang Chen","year":"2017"},{"key":"bib28","volume-title":"Proceedings of the 21st International Conference on Computational Linguistics and the 44th Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Liang Percy","year":"2006"},{"key":"bib29","volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Misra Dipendra","year":"2018"},{"key":"bib30","volume-title":"Proceedings of the 34th International Conference on Machine Learning (ICML)","author":"Mou Lili","year":"2017"},{"key":"bib31","volume-title":"Computer Intensive Methods for Testing Hypotheses: An Introduction","author":"Noreen Eric W.","year":"1989"},{"key":"bib32","volume-title":"Advances in Neural Information Processing Systems (NIPS)","author":"Norouzi Mohammad","year":"2016"},{"key":"bib33","doi-asserted-by":"crossref","unstructured":"Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2001, BLEU: A method for automatic evaluation of machine translation. Technical Report IBM Research Division Technical Report, RC22176 (W0190-022), Yorktown Heights, NY.","DOI":"10.3115\/1073083.1073135"},{"key":"bib34","volume-title":"Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (ACL-IJCNLP)","author":"Pasupat Panupong","year":"2015"},{"key":"bib35","volume-title":"Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Rajpurkar Pranav","year":"2016"},{"key":"bib36","volume-title":"International Conference on Learning Representations (ICLR)","author":"Ranzato Marc\u2019Aurelio","year":"2016"},{"key":"bib37","volume-title":"Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Schamoni Shigehiko","year":"2014"},{"key":"bib38","volume-title":"Proceedings of the Software Demonstrations of the 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL)","author":"Sennrich Rico","year":"2017"},{"key":"bib39","volume-title":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Sennrich Rico","year":"2016"},{"key":"bib40","volume-title":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Shen Shiqi","year":"2016"},{"key":"bib41","volume-title":"Proceedings of the COLING\/ACL 2006 Main Conference Poster Sessions","author":"Smith David A.","year":"2006"},{"key":"bib42","volume-title":"Advances in Neural Information Processing Systems (NIPS)","author":"Sutskever Ilya","year":"2014"},{"key":"bib43","volume-title":"Proceedings of the 22nd International Conference on Machine Learning (ICML)","author":"Taskar Ben","year":"2005"},{"key":"bib44","volume-title":"Advances in Neural Information Processing Systems (NIPS)","author":"Taskar Ben","year":"2004"},{"key":"bib45","first-page":"229","volume":"20","author":"Williams Ronald J.","year":"1992","journal-title":"Machine Learning"},{"key":"bib46","volume-title":"Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Wiseman Sam","year":"2016"},{"key":"bib47","volume-title":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Yang Zhilin","year":"2017"},{"key":"bib48","volume":"1212","author":"Zeiler Matthew D.","year":"2012","journal-title":"ArXiv e-prints"}],"container-title":["Transactions of the Association for Computational Linguistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mitpressjournals.org\/doi\/pdf\/10.1162\/tacl_a_00265","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,12]],"date-time":"2021-03-12T21:39:22Z","timestamp":1615585162000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/tacl\/article\/43505"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":48,"alternative-id":["10.1162\/tacl_a_00265"],"URL":"https:\/\/doi.org\/10.1162\/tacl_a_00265","relation":{},"ISSN":["2307-387X"],"issn-type":[{"value":"2307-387X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,11]]}}}