Towards a One-stop Solution to Both Aspect Extraction and Sentiment Analysis Tasks with Neural Multi-task Learning

Previous studies usually divided aspect-based sentiment analysis into several subtasks in pipeline, i.e., first aspect term and/or opinion term extraction, then aspect-based sentiment prediction, resulting in error propagation and external resources dependency. To overcome the problems mentioned above, in this work we present a novel one-stop solution on aspect-based sentiment analysis. Specifically, we propose a novel multi-task neural learning framework to jointly tackle aspect extraction and sentiment prediction subtasks at the same time, and leverage attention mechanisms to learn the joint representation of aspect-sentiment relationship. We have conducted extensive comparative experiments on two benchmark datasets from SemEva1–2014. The experiment results demonstrate the effectiveness of our proposed solution. Especially, our multi-task model outperforms the state-of-the-art systems on aspect extraction subtask.

[1]  Zhiqiang Toh,et al.  DLIREC: Aspect Term Extraction and Term Polarity Classification System , 2014, *SEMEVAL.

[2]  Eric Nichols,et al.  Named Entity Recognition with Bidirectional LSTM-CNNs , 2015, TACL.

[3]  Bing Liu,et al.  Opinion observer: analyzing and comparing opinions on the Web , 2005, WWW '05.

[4]  Cícero Nogueira dos Santos,et al.  Learning Character-level Representations for Part-of-Speech Tagging , 2014, ICML.

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

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

[7]  Yoshua Bengio,et al.  Attention-Based Models for Speech Recognition , 2015, NIPS.

[8]  Ting Liu,et al.  Aspect Level Sentiment Classification with Deep Memory Network , 2016, EMNLP.

[9]  Yoshua Bengio,et al.  Learning long-term dependencies with gradient descent is difficult , 1994, IEEE Trans. Neural Networks.

[10]  Razvan Pascanu,et al.  On the difficulty of training recurrent neural networks , 2012, ICML.

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

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

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

[14]  Jason Weston,et al.  A unified architecture for natural language processing: deep neural networks with multitask learning , 2008, ICML '08.

[15]  J. Keziya Rani,et al.  Mining Opinion Features in Customer Reviews. , 2016 .

[16]  Joachim Wagner,et al.  DCU: Aspect-based Polarity Classification for SemEval Task 4 , 2014, *SEMEVAL.

[17]  Sinno Jialin Pan,et al.  Multi-task memory networks for category-specific aspect and opinion terms co-extraction , 2017 .

[18]  Lei Zhang,et al.  A Survey of Opinion Mining and Sentiment Analysis , 2012, Mining Text Data.

[19]  Xuanjing Huang,et al.  Recurrent Neural Network for Text Classification with Multi-Task Learning , 2016, IJCAI.

[20]  Xiaokui Xiao,et al.  Coupled Multi-Layer Attentions for Co-Extraction of Aspect and Opinion Terms , 2017, AAAI.

[21]  Jürgen Schmidhuber,et al.  Learning to forget: continual prediction with LSTM , 1999 .

[22]  Lidong Bing,et al.  Recurrent Attention Network on Memory for Aspect Sentiment Analysis , 2017, EMNLP.

[23]  Rohini K. Srihari,et al.  OpinionMiner: a novel machine learning system for web opinion mining and extraction , 2009, KDD.

[24]  Caroline Brun,et al.  XRCE: Hybrid Classification for Aspect-based Sentiment Analysis , 2014, *SEMEVAL.

[25]  Gerard de Melo,et al.  Sentiment-Aspect Extraction based on Restricted Boltzmann Machines , 2015, ACL.

[26]  Hao Yu,et al.  Structure-Aware Review Mining and Summarization , 2010, COLING.

[27]  Xin Li,et al.  Deep Multi-Task Learning for Aspect Term Extraction with Memory Interaction , 2017, EMNLP.

[28]  Josef Steinberger,et al.  UWB: Machine Learning Approach to Aspect-Based Sentiment Analysis , 2014, SemEval@COLING.

[29]  Li Zhao,et al.  Attention-based LSTM for Aspect-level Sentiment Classification , 2016, EMNLP.

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

[31]  Xiaocheng Feng,et al.  Effective LSTMs for Target-Dependent Sentiment Classification , 2015, COLING.

[32]  Ting Liu,et al.  Document Modeling with Gated Recurrent Neural Network for Sentiment Classification , 2015, EMNLP.

[33]  Guillaume Lample,et al.  Neural Architectures for Named Entity Recognition , 2016, NAACL.

[34]  Yoon Kim,et al.  Convolutional Neural Networks for Sentence Classification , 2014, EMNLP.

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

[36]  Tiejun Zhao,et al.  Target-dependent Twitter Sentiment Classification , 2011, ACL.