{"type":"ScholarlyArticle","title":"Inference-Masked Loss for Deep Structured Output Learning","authors":[{"name":"Quan Guo","slug":"quan-guo","given":"Quan","family":"Guo","affiliation":"Michigan State University"},{"name":"Hossein Rajaby Faghihi","slug":"hossein-rajaby-faghihi","given":"Hossein","family":"Rajaby Faghihi","affiliation":"Michigan State University"},{"name":"Yue Zhang","slug":"yue-zhang","given":"Yue","family":"Zhang","affiliation":"Michigan State University"},{"name":"Andrzej Uszok","slug":"andrzej-uszok","given":"Andrzej","family":"Uszok","affiliation":"Florida Institute for Human and Machine Cognition"},{"name":"Parisa Kordjamshidi","slug":"parisa-kordjamshidi","given":"Parisa","family":"Kordjamshidi","affiliation":"Michigan State University"}],"abstract":"Structured learning algorithms usually involve an inference phase that selects the best global output variables assignments based on the local scores of all possible assignments.\r\nWe extend deep neural networks with structured learning to combine the power of learning representations and leveraging the use of domain knowledge in the form of output constraints during training.\r\nIntroducing a non-differentiable inference module to gradient-based training is a critical challenge.\r\nCompared to using conventional loss functions that penalize every local error independently, we propose an inference-masked loss that takes into account the effect of inference and does not penalize the local errors that can be corrected by the inference.\r\nWe empirically show the inference-masked loss combined with the negative log-likelihood loss improves the performance on different tasks, namely entity relation recognition on CoNLL04 and ACE2005 corpora, and spatial role labeling on CLEF 2017 mSpRL dataset. We show the proposed approach helps to achieve better generalizability, particularly in the low-data regime.","doi":"10.24963/ijcai.2020/382","url":"https://ijcai.org/proceedings/2020/382","pdf":"https://ijcai.org/proceedings/2020/0382.pdf","markdown":"https://ijcai.org/proceedings/2020/382.md","bibtex":"https://ijcai.org/proceedings/2020/bibtex/382","volume":{"slug":"2020","title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2020","url":"https://ijcai.org/proceedings/2020/","year":2020,"location":"Yokohama","dates":"January 2021 (postponed from 11-17 July 2020)","editors":"Christian Bessiere","isbn":"978-0-9992411-6-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2020"},"section":"Machine Learning","track":"Main track","number":382,"pages":{"first":2754,"last":2761},"keywords":["Machine Learning: Deep Learning","Machine Learning: Structured Prediction","Machine Learning: Relational Learning"],"videos":[{"label":"Video","url":"https://videos.ijcai20.org/24217/file_24217.m3u8","length_sec":286,"provider":"hls"}],"references":[{"position":1,"raw":"[Akbik et al., 2018] Alan Akbik, Duncan Blythe, and Roland Vollgraf. Contextual string embeddings for se- quence labeling. In COLING 2018, 27th International Conference on Computational Linguistics, pages 1638- 1649, 2018.","title":"Contextual string embeddings for sequence labeling","authors":"Alan Akbik, Duncan Blythe, Roland Vollgraf","year":"2018","venue":"COLING 2018, 27th International Conference on Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Chang et al., 2012] Ming-Wei Chang, Lev Ratinov, and Dan Roth. Structured learning with constrained condi- tional models. Machine learning, 88(3):399-431, 2012.","title":"Structured learning with constrained conditional models","authors":"Ming-Wei Chang, Lev Ratinov, Dan Roth","year":"2012","venue":"Machine learning","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chen et al., 2015] Liang-Chieh Chen, Alexander Schwing, Alan Yuille, and Raquel Urtasun. Learning deep structured models. In Francis Bach and David Blei, editors, Pro- ceedings of the 32nd International Conference on Machine Learning, volume 37 of Proceedings of Machine Learn- ing Research, pages 1785-1794, Lille, France, 07-09 Jul 2015. PMLR.","title":"Learning deep structured models","authors":"Liang-Chieh Chen, Alexander Schwing, Alan Yuille, Raquel Urtasun","year":"2015","venue":"Proceedings of the 32nd International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Cho et al., 2014] Kyunghyun Cho, Bart van Merriënboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. Learning phrase representations using RNN encoder-decoder for statisti- cal machine translation. In Proceedings of the 2014 Con- ference on Empirical Methods in Natural Language Pro- cessing (EMNLP), pages 1724-1734, Doha, Qatar, Octo- ber 2014. Association for Computational Linguistics.","title":"Learning phrase representations using RNN encoder-decoder for statistical machine translation","authors":"Cho","year":"2014","venue":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Collins, 2002] Michael Collins. Discriminative training methods for hidden Markov models: Theory and experi- ments with perceptron algorithms. In Proceedings of the 2002 Conference on Empirical Methods in Natural Lan- guage Processing (EMNLP 2002), pages 1-8. Association for Computational Linguistics, July 2002.","title":"Discriminative training methods for hidden Markov models: Theory and experiments with perceptron algorithms","authors":"Michael Collins","year":"2002","venue":"Proceedings of the 2002 Conference on Empirical Methods in Natural Language Processing (EMNLP 2002)","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Devlin et al., 2019] Jacob Devlin, Ming-Wei Chang, Ken- ton Lee, and Kristina Toutanova. Bert: Pre-training of deep bidirectional transformers for language understand- ing. In NAACL-HLT, 2019.","title":"Bert: Pre-training of deep bidirectional transformers for language understanding","authors":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, Kristina Toutanova","year":"2019","venue":"NAACL-HLT","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Edunov et al., 2018] Sergey Edunov, Myle Ott, Michael Auli, David Grangier, and Marc'Aurelio Ranzato. Clas- sical structured prediction losses for sequence to sequence learning. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computa- tional Linguistics: Human Language Technologies, Vol- ume 1 (Long Papers), pages 355-364. Association for Computational Linguistics, June 2018.","title":"Classical structured prediction losses for sequence to sequence learning","authors":"Sergey Edunov, Myle Ott, Michael Auli, David Grangier, Marc'aurelio Ranzato","year":"2018","venue":"Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Gimpel and Smith, 2010] Kevin Gimpel and Noah A. Smith. Softmax-margin CRFs: Training log-linear mod- els with cost functions. In Human Language Technolo- gies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, pages 733-736, Los Angeles, California, June 2010. As- sociation for Computational Linguistics.","title":"Softmax-margin CRFs: Training log-linear models with cost functions","authors":"Kevin Gimpel, Noah A Smith","year":"2010","venue":"Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Guo et al., 2019] Quan Guo, Andrzej Uszok, and Parisa Ko- rdjamshidi. From ontologies to learning-based programs. In IJCAI 2019 Workshop on DeLBP, 2019.","title":"From ontologies to learning-based programs","authors":"Quan Guo, Andrzej Uszok, Parisa Kordjamshidi","year":"2019","venue":"IJCAI 2019 Workshop on DeLBP","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Ilharco et al., 2019] Gabriel Ilharco, Yuan Zhang, and Jason Baldridge. Large-scale representation learning from vi- sually grounded untranscribed speech. In Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL), pages 55-65. Association for Compu- tational Linguistics, November 2019.","title":"Large-scale representation learning from visually grounded untranscribed speech","authors":"Gabriel Ilharco, Yuan Zhang, Jason Baldridge","year":"2019","venue":"Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Kingma and Ba, 2014] Diederik P Kingma and Jimmy Ba. Adam: A method for stochastic optimization. In ICLR, 2014.","title":"Adam: A method for stochastic optimization","authors":"P Diederik, Jimmy Kingma, Ba","year":"2014","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Kordjamshidi et al., 2015] Parisa Kordjamshidi, Hao Wu, and Dan Roth. Saul: Towards declarative learning based programming. In Proc. of the International Joint Confer- ence on Artificial Intelligence (IJCAI), 7 2015.","title":"Saul: Towards declarative learning based programming","authors":"Parisa Kordjamshidi, Hao Wu, Dan Roth","year":"2015","venue":"Proc. of the International Joint Conference on Artificial Intelligence (IJCAI)","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Kordjamshidi et al., 2017a] Parisa Kordjamshidi, Taher Rahgooy, Marie-Francine Moens, James Pustejovsky, Umar Manzoor, and Kirk Roberts. Clef 2017: Multimodal spatial role labeling (msprl) task overview. In Inter- national Conference of the Cross-Language Evaluation Forum for European Languages, pages 367-376. Springer, 2017.","title":"Clef 2017: Multimodal spatial role labeling (msprl) task overview","authors":"Kordjamshidi","year":"2017","venue":"International Conference of the Cross-Language Evaluation Forum for European Languages","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Kordjamshidi et al., 2017b] Parisa Kordjamshidi, Martijn van Otterlo, and Marie-Francine Moens. Spatial Role La- beling Annotation Scheme, pages 1025-1052. Springer Netherlands, Dordrecht, 2017.","title":"Spatial Role Labeling Annotation Scheme","authors":"Kordjamshidi","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Li and Ji, 2014] Qi Li and Heng Ji. Incremental joint ex- traction of entity mentions and relations. In Proceedings of the 52nd Annual Meeting of the Association for Compu- tational Linguistics (Volume 1: Long Papers), pages 402- 412, 2014.","title":"Incremental joint extraction of entity mentions and relations","authors":"Ji ; ] Qi Li, Heng Li, Ji","year":"2014","venue":"Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Li and Srikumar, 2019] Tao Li and Vivek Srikumar. Aug- menting neural networks with first-order logic. In Pro- ceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 292-302, Florence, Italy, July 2019. Association for Computational Linguis- tics.","title":"Augmenting neural networks with first-order logic","authors":"Srikumar ; ] Tao Li, Vivek Li, Srikumar","year":"2019","venue":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Liang et al., 2019] Chen Liang, Ni Lao, Wang Ling, Zita Marinho, Yuandong Tian, Lu Wang, Jason D Williams, Audrey Durand, and Andre Martins. Deep Reinforcement Learning Meets Structured Prediction, 2019.","title":"Deep Reinforcement Learning Meets Structured Prediction","authors":"Chen Liang, Ni Lao, Wang Ling, Zita Marinho, Yuandong Tian, Lu Wang, Jason D Williams, Audrey Durand, Andre Martins","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Ma and Hovy, 2016] Xuezhe Ma and Eduard Hovy. End- to-end sequence labeling via bi-directional LSTM-CNNs- CRF. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1064-1074, Berlin, Germany, August 2016. Association for Computational Linguistics.","title":"Xuezhe Ma and Eduard Hovy. Endto-end sequence labeling via bi-directional LSTM-CNNs-CRF","authors":"Hovy Ma","year":"2016","venue":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Maes et al., 2009] Francis Maes, Ludovic Denoyer, and Patrick Gallinari. Structured prediction with reinforcement learning. Machine learning, 77(2-3):271, 2009.","title":"Structured prediction with reinforcement learning","authors":"Francis Maes, Ludovic Denoyer, Patrick Gallinari","year":"2009","venue":"Machine learning","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Manzoor and Kordjamshidi, 2018] Umar Manzoor and Parisa Kordjamshidi. Anaphora resolution for improving spatial relation extraction from text. In Proceedings of the First International Workshop on Spatial Language Understanding, pages 53-62, 2018.","title":"Anaphora resolution for improving spatial relation extraction from text","authors":"Kordjamshidi Manzoor, Umar Manzoor, Parisa Kordjamshidi","year":"2018","venue":"Proceedings of the First International Workshop on Spatial Language Understanding","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Marquez Neila et al., 2017] Pablo Marquez Neila, Mathieu Salzmann, and Pascal Fua. Imposing hard constraints on deep networks: Promises and limitations. In CVPR Work- shop on Negative Results in Computer Vision, 2017.","title":"Imposing hard constraints on deep networks: Promises and limitations","authors":"Neila Marquez","year":"2017","venue":"CVPR Workshop on Negative Results in Computer Vision","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Muralidhar et al., 2019] Nikhil Muralidhar, Moham- mad Raihanul Islam, Manish Marwah, Anuj Karpatne, and Naren Ramakrishnan. Incorporating Prior Domain Knowledge into Deep Neural Networks. Proceedings - 2018 IEEE International Conference on Big Data, Big Data 2018, pages 36-45, 2019.","title":"Incorporating Prior Domain Knowledge into Deep Neural Networks","authors":"Nikhil Muralidhar, Mohammad Raihanul Islam, Manish Marwah, Anuj Karpatne, Naren Ramakrishnan","year":"2019","venue":"Proceedings -2018 IEEE International Conference on Big Data, Big Data 2018","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Nandwani et al., 2019] Yatin Nandwani, Abhishek Pathak, Mausam, and Parag Singla. A primal dual formula- tion for deep learning with constraints. In H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alché Buc, E. Fox, and R. Garnett, editors, Advances in Neural Information Processing Systems 32, pages 12157-12168.","title":"A primal dual formulation for deep learning with constraints","authors":"Yatin Nandwani, Abhishek Pathak, Mausam, Parag Singla","year":null,"venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Pathak et al., 2015] Deepak Pathak, Philipp Krahenbuhl, and Trevor Darrell. Constrained convolutional neural net- works for weakly supervised segmentation. In Proceed- ings of the 2015 IEEE International Conference on Com- puter Vision (ICCV), ICCV '15, pages 1796-1804, Wash- ington, DC, USA, 2015. IEEE Computer Society.","title":"Constrained convolutional neural networks for weakly supervised segmentation","authors":"Deepak Pathak, Philipp Krahenbuhl, Trevor Darrell","year":"2015","venue":"Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV), ICCV '15","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Pennington et al., 2014] Jeffrey Pennington, Richard Socher, and Christopher D. Manning. Glove: Global vectors for word representation. In Empirical Meth- ods in Natural Language Processing (EMNLP), pages 1532-1543, 2014.","title":"Glove: Global vectors for word representation","authors":"Jeffrey Pennington, Richard Socher, Christopher D Manning","year":"2014","venue":"Empirical Methods in Natural Language Processing (EMNLP)","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Rizzolo and Roth, 2007] N. Rizzolo and D. Roth. Model- ing discriminative global inference. In Proc. of the IEEE International Conference on Semantic Computing (ICSC), pages 597-604, Irvine, California, 9 2007. IEEE.","title":"Modeling discriminative global inference","authors":"N Rizzolo, D Roth","year":"2007","venue":"Proc. of the IEEE International Conference on Semantic Computing (ICSC)","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Roth and Yih, 2004] D. Roth and W. Yih. A linear program- ming formulation for global inference in natural language tasks. In Hwee Tou Ng and Ellen Riloff, editors, Proc. of the Conference on Computational Natural Language Learning (CoNLL), pages 1-8. Association for Computa- tional Linguistics, 2004.","title":"A linear programming formulation for global inference in natural language tasks","authors":"D Roth, W Yih","year":"2004","venue":"Proc. of the Conference on Computational Natural Language Learning (CoNLL)","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Roth and Yih, 2005] D. Roth and W. Yih. Integer linear programming inference for conditional random fields. In Proc. of the International Conference on Machine Learn- ing (ICML), pages 737-744, 2005.","title":"Integer linear programming inference for conditional random fields","authors":"D Roth, W Yih","year":"2005","venue":"Proc. of the International Conference on Machine Learning (ICML)","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Shen et al., 2019] Yikang Shen, Shawn Tan, Alessandro Sordoni, and Aaron Courville. Ordered neurons: Integrat- ing tree structures into recurrent neural networks. In Inter- national Conference on Learning Representations, 2019.","title":"Ordered neurons: Integrating tree structures into recurrent neural networks","authors":"Shen","year":"2019","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Straková et al., 2019] Jana Straková, Milan Straka, and Jan Hajič. Neural architectures for nested ner through lin- earization. arXiv preprint arXiv:1908.06926, 2019.","title":"Neural architectures for nested ner through linearization","authors":"Jana Straková, Milan Straka, Jan Hajič","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Sutton and McCallum, 2006] Charles Sutton and Andrew McCallum. An introduction to conditional random fields for relational learning. In Lise Getoor and Ben Taskar, ed- itors, Introduction to Statistical Relational Learning. MIT Press, 2006.","title":"An introduction to conditional random fields for relational learning","authors":"Sutton, Mccallum, Charles Sutton, Andrew Mccallum","year":"2006","venue":"itors, Introduction to Statistical Relational Learning","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Weiss et al., 2015] David Weiss, Chris Alberti, Michael Collins, and Slav Petrov. Structured training for neural network transition-based parsing. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 323-333. Association for Computational Linguis- tics, July 2015.","title":"Structured training for neural network transition-based parsing","authors":"David Weiss, Chris Alberti, Michael Collins, Slav Petrov","year":"2015","venue":"Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Wu et al., 2019] Zonghan Wu, Shirui Pan, Fengwen Chen, Guodong Long, Chengqi Zhang, and Philip S Yu. A comprehensive survey on graph neural networks. arXiv preprint arXiv:1901.00596, 2019.","title":"A comprehensive survey on graph neural networks","authors":"Wu","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Yang et al., 2019] Yinfei Yang, Gustavo Hernan- dez Abrego, Steve Yuan, Mandy Guo, Qinlan Shen, Daniel Cer, Yun-hsuan Sung, Brian Strope, and Ray Kurzweil. Improving multilingual sentence embed- ding using bi-directional dual encoder with additive margin softmax. In Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelli- gence, IJCAI-19, pages 5370-5378. International Joint Conferences on Artificial Intelligence Organization, 7 2019.","title":"Improving multilingual sentence embedding using bi-directional dual encoder with additive margin softmax","authors":"Yang","year":"2019","venue":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI-19","doi":null,"url":null,"internal_url":"/proceedings/2019/746"}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}