Forward and Backward Knowledge Transfer for Sentiment Classification

This paper studies the problem of learning a sequence of sentiment classification tasks. The learned knowledge from each task is retained and used to help future or subsequent task learning. This learning paradigm is called Lifelong Learning (LL). However, existing LL methods either only transfer knowledge forward to help future learning and do not go back to improve the model of a previous task or require the training data of the previous task to retrain its model to exploit backward/reverse knowledge transfer. This paper studies reverse knowledge transfer of LL in the context of naive Bayesian (NB) classification. It aims to improve the model of a previous task by leveraging future knowledge without retraining using its training data. This is done by exploiting a key characteristic of the generative model of NB. That is, it is possible to improve the NB classifier for a task by improving its model parameters directly by using the retained knowledge from other tasks. Experimental results show that the proposed method markedly outperforms existing LL baselines.

[1]  J. Heckman.  Sample selection bias as a specification error , 1979 .

[2]  Rich Caruana,et al.  Multitask Learning , 1998, Encyclopedia of Machine Learning and Data Mining.

[3]  Sebastian Thrun,et al.  Learning to Classify Text from Labeled and Unlabeled Documents , 1998, AAAI/IAAI.

[4]  Sebastian Thrun,et al.  Lifelong Learning Algorithms , 1998, Learning to Learn.

[5]  R. French.  Catastrophic forgetting in connectionist networks , 1999, Trends in Cognitive Sciences.

[6]  Roberto J. Bayardo,et al.  Athena: Mining-Based Interactive Management of Text Database , 2000, EDBT.

[7]  Bo Pang,et al.  Thumbs up? Sentiment Classification using Machine Learning Techniques , 2002, EMNLP.

[8]  Bianca Zadrozny,et al.  Learning and evaluating classifiers under sample selection bias , 2004, ICML.

[9]  Massimiliano Pontil,et al.  Regularized multi--task learning , 2004, KDD.

[10]  Lillian Lee,et al.  Opinion Mining and Sentiment Analysis , 2008, Found. Trends Inf. Retr..

[11]  John Blitzer,et al.  Biographies, Bollywood, Boom-boxes and Blenders: Domain Adaptation for Sentiment Classification , 2007, ACL.

[12]  Sabine Bergler,et al.  When Specialists and Generalists Work Together: Overcoming Domain Dependence in Sentiment Tagging , 2008, ACL.

[13]  Chengqing Zong,et al.  Multi-domain Sentiment Classification , 2008, ACL.

[14]  Hongbo Xu,et al.  Adapting Naive Bayes to Domain Adaptation for Sentiment Analysis , 2009, ECIR.

[15]  Qiong Wu,et al.  Graph Ranking for Sentiment Transfer , 2009, ACL.

[16]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[17]  Qiang Yang,et al.  Cross-domain sentiment classification via spectral feature alignment , 2010, WWW '10.

[18]  Harith Alani,et al.  Automatically Extracting Polarity-Bearing Topics for Cross-Domain Sentiment Classification , 2011, ACL.

[19]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[20]  Wen Fan,et al.  Probability adjustment Naïve Bayes algorithm based on nondomain-specific sentiment and evaluation word for domain-transfer sentiment analysis , 2011, 2011 Eighth International Conference on Fuzzy Systems and Knowledge Discovery (FSKD).

[21]  Yoshua Bengio,et al.  Domain Adaptation for Large-Scale Sentiment Classification: A Deep Learning Approach , 2011, ICML.

[22]  Rui Xia,et al.  A POS-based Ensemble Model for Cross-domain Sentiment Classification , 2011, IJCNLP.

[23]  Danushka Bollegala,et al.  Using Multiple Sources to Construct a Sentiment Sensitive Thesaurus for Cross-Domain Sentiment Classification , 2011, ACL.

[24]  Qiang Yang,et al.  Cross-Domain Co-Extraction of Sentiment and Topic Lexicons , 2012, ACL.

[25]  Qiang Yang,et al.  Lifelong Machine Learning Systems: Beyond Learning Algorithms , 2013, AAAI Spring Symposium: Lifelong Machine Learning.

[26]  Eric Eaton,et al.  ELLA: An Efficient Lifelong Learning Algorithm , 2013, ICML.

[27]  Guodong Zhou,et al.  Active Learning for Cross-domain Sentiment Classification , 2013, IJCAI.

[28]  Bing Liu,et al.  Topic Modeling using Topics from Many Domains, Lifelong Learning and Big Data , 2014, ICML.

[29]  Bing Liu,et al.  Lifelong Learning for Sentiment Classification , 2015, ACL.

[30]  Christoph H. Lampert,et al.  Lifelong Learning with Non-i.i.d. Tasks , 2015, NIPS.

[31]  Xinlei Chen,et al.  Never-Ending Learning , 2012, ECAI.

[32]  Bing Liu,et al.  Lifelong machine learning: a paradigm for continuous learning , 2017, Frontiers of Computer Science.

[33]  Shuai Wang,et al.  Learning Cumulatively to Become More Knowledgeable , 2016, KDD.

[34]  Eric Eaton,et al.  Using Task Features for Zero-Shot Knowledge Transfer in Lifelong Learning , 2016, IJCAI.

[35]  Mike Thelwall,et al.  Sentiment Analysis Is a Big Suitcase , 2017, IEEE Intelligent Systems.

[36]  Lei Zhang,et al.  Sentiment Analysis and Opinion Mining , 2017, Encyclopedia of Machine Learning and Data Mining.

[37]  Lei Shu,et al.  Lifelong Learning CRF for Supervised Aspect Extraction , 2017, ACL.

[38]  Razvan Pascanu,et al.  Overcoming catastrophic forgetting in neural networks , 2016, Proceedings of the National Academy of Sciences.

[39]  Tinne Tuytelaars,et al.  Expert Gate: Lifelong Learning with a Network of Experts , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[40]  Sebastian Ruder,et al.  An Overview of Multi-Task Learning in Deep Neural Networks , 2017, ArXiv.

[41]  Rui Xia,et al.  Distantly Supervised Lifelong Learning for Large-Scale Social Media Sentiment Analysis , 2017, IEEE Transactions on Affective Computing.

[42]  Jun Yan,et al.  Active Sentiment Domain Adaptation , 2017, ACL.

[43]  Yu Zhang,et al.  A Survey on Multi-Task Learning , 2017, IEEE Transactions on Knowledge and Data Engineering.

[44]  Eric Eaton,et al.  Lifelong Learning with Gaussian Processes , 2017, ECML/PKDD.

[45]  Yu Zhang,et al.  Hierarchical Attention Transfer Network for Cross-Domain Sentiment Classification , 2018, AAAI.

[46]  Isabelle Augenstein,et al.  Multi-Task Learning of Pairwise Sequence Classification Tasks over Disparate Label Spaces , 2018, NAACL.

[47]  Philip S. Yu,et al.  Lifelong Domain Word Embedding via Meta-Learning , 2018, IJCAI.

[48]  Hwee Tou Ng,et al.  Adaptive Semi-supervised Learning for Cross-domain Sentiment Classification , 2018, EMNLP.

[49]  Gan Sun,et al.  Active Lifelong Learning With "Watchdog" , 2018, AAAI.

[50]  Richard E. Turner,et al.  Variational Continual Learning , 2017, ICLR.

[51]  Enhong Chen,et al.  Sentiment Classification by Leveraging the Shared Knowledge from a Sequence of Domains , 2019, DASFAA.

[52]  Gary Anthes,et al.  Lifelong learning in artificial neural networks , 2019, Commun. ACM.

[53]  Marc'Aurelio Ranzato,et al.  Efficient Lifelong Learning with A-GEM , 2018, ICLR.

[54]  Stefan Wermter,et al.  Continual Lifelong Learning with Neural Networks: A Review , 2019, Neural Networks.

[55]  Xiaodong Liu,et al.  Multi-Task Deep Neural Networks for Natural Language Understanding , 2019, ACL.