Understanding Gating Operations in Recurrent Neural Networks through Opinion Expression Extraction

Extracting opinion expressions from text is an essential task of sentiment analysis, which is usually treated as one of the word-level sequence labeling problems. In such problems, compositional models with multiplicative gating operations provide efficient ways to encode the contexts, as well as to choose critical information. Thus, in this paper, we adopt Long Short-Term Memory (LSTM) recurrent neural networks to address the task of opinion expression extraction and explore the internal mechanisms of the model. The proposed approach is evaluated on the Multi-Perspective Question Answering (MPQA) opinion corpus. The experimental results demonstrate improvement over previous approaches, including the state-of-the-art method based on simple recurrent neural networks. We also provide a novel micro perspective to analyze the run-time processes and gain new insights into the advantages of LSTM selecting the source of information with its flexible connections and multiplicative gating operations.

[1]  Claire Cardie,et al.  Joint Modeling of Opinion Expression Extraction and Attribute Classification , 2014, Transactions of the Association for Computational Linguistics.

[2]  Claire Cardie,et al.  Extracting Opinion Expressions with semi-Markov Conditional Random Fields , 2012, EMNLP.

[3]  Claire Cardie,et al.  Annotating Expressions of Opinions and Emotions in Language , 2005, Lang. Resour. Evaluation.

[4]  Jürgen Schmidhuber,et al.  Framewise phoneme classification with bidirectional LSTM and other neural network architectures , 2005, Neural Networks.

[5]  Kuldip K. Paliwal,et al.  Bidirectional recurrent neural networks , 1997, IEEE Trans. Signal Process..

[6]  Jeffrey L. Elman,et al.  Finding Structure in Time , 1990, Cogn. Sci..

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

[8]  Giovanni Soda,et al.  Exploiting the past and the future in protein secondary structure prediction , 1999, Bioinform..

[9]  Claire Cardie,et al.  Hierarchical Sequential Learning for Extracting Opinions and Their Attributes , 2010, ACL.

[10]  Claire Cardie,et al.  Opinion Mining with Deep Recurrent Neural Networks , 2014, EMNLP.

[11]  Jürgen Schmidhuber,et al.  LSTM: A Search Space Odyssey , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[12]  Richard Johansson,et al.  Relational Features in Fine-Grained Opinion Analysis , 2013, CL.

[13]  Claire Cardie,et al.  Joint Extraction of Entities and Relations for Opinion Recognition , 2006, EMNLP.

[14]  Christopher D. Manning,et al.  Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks , 2015, ACL.

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

[16]  Richard Johansson,et al.  Syntactic and Semantic Structure for Opinion Expression Detection , 2010, CoNLL.

[17]  Richard Johansson,et al.  Extracting Opinion Expressions and Their Polarities - Exploration of Pipelines and Joint Models , 2011, ACL.

[18]  Claire Cardie,et al.  Identifying Expressions of Opinion in Context , 2007, IJCAI.

[19]  Wojciech Zaremba,et al.  An Empirical Exploration of Recurrent Network Architectures , 2015, ICML.

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

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

[22]  Janyce Wiebe,et al.  Recognizing Contextual Polarity in Phrase-Level Sentiment Analysis , 2005, HLT.

[23]  Ellen Riloff,et al.  Creating Subjective and Objective Sentence Classifiers from Unannotated Texts , 2005, CICLing.

[24]  Geoffrey E. Hinton,et al.  Speech recognition with deep recurrent neural networks , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[25]  Claire Cardie,et al.  Modeling Compositionality with Multiplicative Recurrent Neural Networks , 2014, ICLR.

[26]  F. Gers,et al.  Long short-term memory in recurrent neural networks , 2001 .

[27]  Christopher Potts,et al.  Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank , 2013, EMNLP.

[28]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.