Recurrent Neural Networks with Auxiliary Labels for Cross-Domain Opinion Target Extraction

Opinion target extraction is a fundamental task in opinion mining. In recent years, neural network based supervised learning methods have achieved competitive performance on this task. However, as with any supervised learning method, neural network based methods for this task cannot work well when the training data comes from a different domain than the test data. On the other hand, some rule-based unsupervised methods have shown to be robust when applied to different domains. In this work, we use rule-based unsupervised methods to create auxiliary labels and use neural network models to learn a hidden representation that works well for different domains. When this hidden representation is used for opinion target extraction, we find that it can outperform a number of strong baselines with a large margin.

[1]  Kilian Q. Weinberger,et al.  Marginalized Denoising Autoencoders for Domain Adaptation , 2012, ICML.

[2]  Maryna Chernyshevich,et al.  IHS R&D Belarus: Cross-domain Extraction of Product Features using Conditional Random Fields , 2014 .

[3]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[4]  Bing Liu,et al.  Mining and summarizing customer reviews , 2004, KDD.

[5]  Suresh Manandhar,et al.  SemEval-2015 Task 12: Aspect Based Sentiment Analysis , 2015, *SEMEVAL.

[6]  Iryna Gurevych,et al.  Sentence and Expression Level Annotation of Opinions in User-Generated Discourse , 2010, ACL.

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

[8]  Claire Cardie,et al.  Joint Inference for Fine-grained Opinion Extraction , 2013, ACL.

[9]  Shafiq R. Joty,et al.  Fine-grained Opinion Mining with Recurrent Neural Networks and Word Embeddings , 2015, EMNLP.

[10]  Ming Zhou,et al.  Unsupervised Word and Dependency Path Embeddings for Aspect Term Extraction , 2016, IJCAI.

[11]  Xiaoyan Zhu,et al.  Movie review mining and summarization , 2006, CIKM '06.

[12]  Andrew McCallum,et al.  Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data , 2001, ICML.

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

[14]  Kim Schouten,et al.  Survey on Aspect-Level Sentiment Analysis , 2016, IEEE Transactions on Knowledge and Data Engineering.

[15]  Iryna Gurevych,et al.  Extracting Opinion Targets in a Single and Cross-Domain Setting with Conditional Random Fields , 2010, EMNLP.

[16]  Miriam Eckert,et al.  The ICWSM 2010 JDPA Sentiment Corpus for the Automotive Domain , 2010 .

[17]  John Blitzer,et al.  Domain Adaptation with Structural Correspondence Learning , 2006, EMNLP.

[18]  Yue Zhang,et al.  Neural Networks for Open Domain Targeted Sentiment , 2015, EMNLP.

[19]  Chun Chen,et al.  Opinion Word Expansion and Target Extraction through Double Propagation , 2011, CL.

[20]  Yi Yang,et al.  Unsupervised Multi-Domain Adaptation with Feature Embeddings , 2015, NAACL.

[21]  Xiaokui Xiao,et al.  Recursive Neural Conditional Random Fields for Aspect-based Sentiment Analysis , 2016, EMNLP.

[22]  Suresh Manandhar,et al.  SemEval-2014 Task 4: Aspect Based Sentiment Analysis , 2014, *SEMEVAL.