Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentence

Aspect-based sentiment analysis (ABSA), which aims to identify fine-grained opinion polarity towards a specific aspect, is a challenging subtask of sentiment analysis (SA). In this paper, we construct an auxiliary sentence from the aspect and convert ABSA to a sentence-pair classification task, such as question answering (QA) and natural language inference (NLI). We fine-tune the pre-trained model from BERT and achieve new state-of-the-art results on SentiHood and SemEval-2014 Task 4 datasets. The source codes are available at https://github.com/HSLCY/ABSA-BERT-pair.

[1]  Alice H. Oh,et al.  Aspect and sentiment unification model for online review analysis , 2011, WSDM '11.

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

[3]  Saif Mohammad,et al.  NRC-Canada-2014: Detecting Aspects and Sentiment in Customer Reviews , 2014, *SEMEVAL.

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

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

[6]  Kiyoaki Shirai,et al.  PhraseRNN: Phrase Recursive Neural Network for Aspect-based Sentiment Analysis , 2015, EMNLP.

[7]  Guillaume Bouchard,et al.  SentiHood: Targeted Aspect Based Sentiment Analysis Dataset for Urban Neighbourhoods , 2016, COLING.

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

[9]  Haris Papageorgiou,et al.  SemEval-2016 Task 5: Aspect Based Sentiment Analysis , 2016, *SEMEVAL.

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

[11]  Björn W. Schuller,et al.  SenticNet 4: A Semantic Resource for Sentiment Analysis Based on Conceptual Primitives , 2016, COLING.

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

[13]  Jason Weston,et al.  Tracking the World State with Recurrent Entity Networks , 2016, ICLR.

[14]  Arkaitz Zubiaga,et al.  TDParse: Multi-target-specific sentiment recognition on Twitter , 2017, EACL.

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

[16]  Timothy Baldwin,et al.  Recurrent Entity Networks with Delayed Memory Update for Targeted Aspect-Based Sentiment Analysis , 2018, NAACL.

[17]  Alec Radford,et al.  Improving Language Understanding by Generative Pre-Training , 2018 .

[18]  Erik Cambria,et al.  Targeted Aspect-Based Sentiment Analysis via Embedding Commonsense Knowledge into an Attentive LSTM , 2018, AAAI.

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