Weakly-Supervised Deep Learning for Domain Invariant Sentiment Classification

The task of learning a sentiment classification model that adapts well to any target domain, different from the source domain, is a challenging problem. Majority of the existing approaches focus on learning a common representation by leveraging both source and target data during training. In this paper, we introduce a two-stage training procedure that leverages weakly supervised datasets for developing simple lift-and-shift-based predictive models without being exposed to the target domain during the training phase. Experimental results show that transfer with weak supervision from a source domain to various target domains provides performance very close to that obtained via supervised training on the target domain itself.

[1]  Awais Athar,et al.  Sentiment Analysis of Citations using Sentence Structure-Based Features , 2011, ACL.

[2]  Vincent Ng,et al.  Mine the Easy, Classify the Hard: A Semi-Supervised Approach to Automatic Sentiment Classification , 2009, ACL.

[3]  Yue Zhang,et al.  Word Segmentation for Chinese Novels , 2015, AAAI.

[4]  Misha Denil,et al.  From Group to Individual Labels Using Deep Features , 2015, KDD.

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

[6]  Bo Pang,et al.  Seeing Stars: Exploiting Class Relationships for Sentiment Categorization with Respect to Rating Scales , 2005, ACL.

[7]  Long Chen,et al.  Weakly-Supervised Deep Embedding for Product Review Sentiment Analysis , 2018, IEEE Transactions on Knowledge and Data Engineering.

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

[9]  Ling Peng,et al.  What do seller manipulations of online product reviews mean to consumers , 2014 .

[10]  Michael Gamon,et al.  Customizing Sentiment Classifiers to New Domains: a Case Study , 2019 .

[11]  Luke S. Zettlemoyer,et al.  Deep Contextualized Word Representations , 2018, NAACL.

[12]  Xuanjing Huang,et al.  Cross-Domain Sentiment Classification with Target Domain Specific Information , 2018, ACL.

[13]  Percy Liang,et al.  Delete, Retrieve, Generate: a Simple Approach to Sentiment and Style Transfer , 2018, NAACL.

[14]  Songbo Tan,et al.  A novel scheme for domain-transfer problem in the context of sentiment analysis , 2007, CIKM '07.

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

[16]  Koby Crammer,et al.  Learning from Multiple Sources , 2006, NIPS.

[17]  Uzay Kaymak,et al.  Multi-lingual support for lexicon-based sentiment analysis guided by semantics , 2014, Decis. Support Syst..

[18]  Ivor W. Tsang,et al.  Domain Adaptation via Transfer Component Analysis , 2009, IEEE Transactions on Neural Networks.

[19]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

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

[21]  Muhammad Taimoor Khan,et al.  Sentiment analysis and the complex natural language , 2016, Complex Adapt. Syst. Model..

[22]  Yi Zheng,et al.  Weakly-Supervised Deep Learning for Customer Review Sentiment Classification , 2016, IJCAI.

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

[24]  Yue Zhang,et al.  Type-Supervised Domain Adaptation for Joint Segmentation and POS-Tagging , 2014, EACL.

[25]  Jianfei Yu,et al.  Learning Sentence Embeddings with Auxiliary Tasks for Cross-Domain Sentiment Classification , 2016, EMNLP.

[26]  Ruslan Salakhutdinov,et al.  Transfer Learning for Sequence Tagging with Hierarchical Recurrent Networks , 2016, ICLR.

[27]  Christopher Potts,et al.  Learning Word Vectors for Sentiment Analysis , 2011, ACL.

[28]  Anton van den Hengel,et al.  Image-Based Recommendations on Styles and Substitutes , 2015, SIGIR.

[29]  ChengXiang Zhai,et al.  A two-stage approach to domain adaptation for statistical classifiers , 2007, CIKM '07.