Transformation Networks for Target-Oriented Sentiment Classification

ACL 2018  ·  Xin Li, Lidong Bing, Wai Lam, Bei Shi ·

Target-oriented sentiment classification aims at classifying sentiment polarities over individual opinion targets in a sentence. RNN with attention seems a good fit for the characteristics of this task, and indeed it achieves the state-of-the-art performance. After re-examining the drawbacks of attention mechanism and the obstacles that block CNN to perform well in this classification task, we propose a new model to overcome these issues. Instead of attention, our model employs a CNN layer to extract salient features from the transformed word representations originated from a bi-directional RNN layer. Between the two layers, we propose a component to generate target-specific representations of words in the sentence, meanwhile incorporate a mechanism for preserving the original contextual information from the RNN layer. Experiments show that our model achieves a new state-of-the-art performance on a few benchmarks.

PDF Abstract ACL 2018 PDF ACL 2018 Abstract


Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Aspect-Based Sentiment Analysis (ABSA) SemEval-2014 Task-4 TNet Restaurant (Acc) 80.79 # 32
Laptop (Acc) 76.01 # 19
Aspect-Based Sentiment Analysis (ABSA) SemEval-2014 Task-4 TNet-LF Restaurant (Acc) 80.79 # 32
Laptop (Acc) 76.01 # 19
Mean Acc (Restaurant + Laptop) 78.4 # 20


No methods listed for this paper. Add relevant methods here