{"type":"ScholarlyArticle","title":"Jumper: Learning When to Make Classification Decision in Reading","authors":[{"name":"Xianggen Liu","slug":"xianggen-liu","given":"Xianggen","family":"Liu","affiliation":"Department of Biomedical Engineering , IDG/McGovern Institute for Brain Research , Tsinghua University"},{"name":"Lili Mou","slug":"lili-mou","given":"Lili","family":"Mou","affiliation":"AdeptMind ."},{"name":"Haotian Cui","slug":"haotian-cui","given":"Haotian","family":"Cui","affiliation":"Department of Biomedical Engineering , IDG/McGovern Institute for Brain Research , Tsinghua University"},{"name":"Zhengdong Lu","slug":"zhengdong-lu","given":"Zhengdong","family":"Lu","affiliation":"DeeplyCurious."},{"name":"Sen Song","slug":"sen-song","given":"Sen","family":"Song","affiliation":"Department of Biomedical Engineering , IDG/McGovern Institute for Brain Research , Tsinghua University; Laboratory of Brain and Intelligence , Tsinghua University"}],"abstract":"In early years, text classification is typically accomplished by feature-based classifiers; recently, neural networks, as powerful classifiers, make it possible to work with raw input as the text stands. In this paper, we propose a novel framework, Jumper, inspired by the cognitive process of text reading, that models text classification as a sequential decision process. Basically, Jumper is a neural system that can scan a piece of text sequentially and make classification decision at the time it chooses. Both the classification and when to make the classification are part of the decision process which are controlled by the policy net and trained with reinforcement learning to maximize the overall classification accuracy. Experimental results show that a properly trained Jumper has the following properties: (1) It can make decisions whenever the evidence is enough, therefore reducing the total text reading by 30~40% and often finding the key rationale of prediction. (2) It can achieve classification accuracy better or comparable to state-of-the-art model in several benchmark and industrial datasets.","doi":"10.24963/ijcai.2018/589","url":"https://ijcai.org/proceedings/2018/589","pdf":"https://ijcai.org/proceedings/2018/0589.pdf","markdown":"https://ijcai.org/proceedings/2018/589.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/589","volume":{"slug":"2018","title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2018","url":"https://ijcai.org/proceedings/2018/","year":2018,"location":"Stockholm","dates":"13-19 July 2018","editors":"Jérôme Lang","isbn":"978-0-9992411-2-7","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2018"},"section":"Natural Language Processing","track":"Main track","number":589,"pages":{"first":4237,"last":4243},"keywords":["Natural Language Processing: Natural Language Processing","Natural Language Processing: Text Classification"],"videos":[],"references":[{"position":1,"raw":"[Cho et al., 2014] Kyunghyun Cho, Bart van Merrienboer, Caglar Gulcehre, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. Learning phrase representations using RNN encoder-decoder for statistical machine translation. EMNLP, page 1724-1734, 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":2,"raw":"[He et al., 2016] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recog- nition. In CVPR, pages 770-778, 2016.","title":"Deep residual learning for image recognition","authors":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun","year":"2016","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Joulin et al., 2017] Armand Joulin, Edouard Grave, Piotr Bojanowski, and Tomas Mikolov. Bag of tricks for effi- cient text classification. In EACL, pages 427-431, 2017.","title":"Bag of tricks for efficient text classification","authors":"Armand Joulin, Edouard Grave, Piotr Bojanowski, Tomas Mikolov","year":"2017","venue":"EACL","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Kim, 2014] Yoon Kim. Convolutional neural networks for sentence classification. In EMNLP, pages 1746-1751, 2014.","title":"Convolutional neural networks for sentence classification","authors":"Yoon Kim","year":"2014","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Lei et al., 2016] Tao Lei, Regina Barzilay, and Tommi Jaakkola. Rationalizing neural predictions. In EMNLP, pages 107-117, 2016.","title":"Rationalizing neural predictions","authors":"Tao Lei, Regina Barzilay, Tommi Jaakkola","year":"2016","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Lin et al., 2017] Zhouhan Lin, Minwei Feng, Cicero Nogueira dos Santos, Mo Yu, Bing Xiang, Bowen Zhou, and Yoshua Bengio. A structured self-attentive sentence embedding. In ICLR, 2017.","title":"A structured self-attentive sentence embedding","authors":"Lin","year":"2017","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Lu et al., 2018] Zhengdong Lu, Xianggen Liu, Haotian Cui, Yukun Yan, and Daqi Zheng. Object-oriented neural pro- gramming (oonp) for document understanding. In ACL, 2018.","title":"Object-oriented neural programming (oonp) for document understanding","authors":"Zhengdong Lu, Xianggen Liu, Haotian Cui, Yukun Yan, Daqi Zheng","year":"2018","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Marcus, 2018] Gary Marcus. Deep learning: A critical ap- praisal. arXiv preprint arXiv:1801.00631, 2018.","title":"Deep learning: A critical appraisal","authors":"Gary Marcus","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Mou et al., 2017] Lili Mou, Zhengdong Lu, Hang Li, and Zhi Jin. Coupling distributed and symbolic execution for natural language queries. In ICML, pages 2518-2526, 2017.","title":"Coupling distributed and symbolic execution for natural language queries","authors":"Lili Mou, Zhengdong Lu, Hang Li, Zhi Jin","year":"2017","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Pang and Lee, 2004] Bo Pang and Lillian Lee. A sentimen- tal education: Sentiment analysis using subjectivity sum- marization based on minimum cuts. In ACL, pages 271- 278, 2004.","title":"A sentimental education: Sentiment analysis using subjectivity summarization based on minimum cuts","authors":"Lee ; Pang, Bo Pang, Lillian Lee","year":"2004","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Pang et al., 2002] Bo Pang, Lillian Lee, and Shivakumar Vaithyanathan. Thumbs up?: Sentiment classification us- ing machine learning techniques. In EMNLP, pages 79- 86, 2002.","title":"Thumbs up?: Sentiment classification using machine learning techniques","authors":"Bo Pang, Lillian Lee, Shivakumar Vaithyanathan","year":"2002","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Pennington et al., 2014] Jeffrey Pennington, Richard Socher, and Christopher D. Manning. GloVe: Global vectors for word representation. In EMNLP, pages 1532-1543, 2014.","title":"GloVe: Global vectors for word representation","authors":"Jeffrey Pennington, Richard Socher, Christopher D Manning","year":"2014","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Rajpurkar et al., 2016] Pranav Rajpurkar, Jian Zhang, Kon- stantin Lopyrev, and Percy Liang. SQuAD: 100,000+ questions for machine comprehension of text. In EMNLP, pages 2383-2392, 2016.","title":"SQuAD: 100,000+ questions for machine comprehension of text","authors":"Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, Percy Liang","year":"2016","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Wang and Manning, 2012] Sida Wang and Christopher D Manning. Baselines and bigrams: Simple, good sentiment and topic classification. In ACL (2), pages 90-94, 2012.","title":"Baselines and bigrams: Simple, good sentiment and topic classification","authors":"Wang, Manning, Sida Wang, Christopher D Manning","year":"2012","venue":"ACL (2)","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Wen et al., 2017] Tsung-Hsien Wen, David Vandyke, Nikola Mrkšić, Milica Gasic, Lina M. Rojas Barahona, Pei-Hao Su, Stefan Ultes, and Steve Young. A network- based end-to-end trainable task-oriented dialogue system. In EACL, pages 438-449, 2017.","title":"A networkbased end-to-end trainable task-oriented dialogue system","authors":"Tsung-Hsien Wen, David Vandyke, Nikola Mrkšić, Milica Gasic, Lina M Rojas Barahona, Pei-Hao Su, Stefan Ultes, Steve Young","year":"2017","venue":"EACL","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Williams, 1992] Ronald J Williams. Simple statistical gradient-following algorithms for connectionist reinforce- ment learning. Machine Learning, 8:229-256, 1992.","title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning","authors":"Williams Ronald","year":"1992","venue":"Machine Learning","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Yu et al., 2017] Adams Wei Yu, Hongrae Lee, and Quoc Le. Learning to skim text. In ACL, pages 1880-1890, 2017.","title":"Learning to skim text","authors":"Adams Wei, Yu, Hongrae Lee, Quoc Le","year":"2017","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Zeng et al., 2014] Daojian Zeng, Kang Liu, Siwei Lai, Guangyou Zhou, and Jun Zhao. Relation classification via convolutional deep neural network. In COLING, pages 2335-2344, 2014.","title":"Relation classification via convolutional deep neural network","authors":"Daojian Zeng, Kang Liu, Siwei Lai, Guangyou Zhou, Jun Zhao","year":"2014","venue":"COLING","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Zhang et al., 2015] Xiang Zhang, Junbo Zhao, and Yann LeCun. Character-level convolutional networks for text classification. In NIPS, pages 649-657, 2015.","title":"Character-level convolutional networks for text classification","authors":"Xiang Zhang, Junbo Zhao, Yann Lecun","year":"2015","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Zhang et al., 2016] Ye Zhang, Iain Marshall, and Byron C Wallace. Rationale-augmented convolutional neural net- works for text classification. In EMNLP, pages 795-804, 2016.","title":"Rationale-augmented convolutional neural networks for text classification","authors":"Zhang","year":"2016","venue":"EMNLP","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}