SentiPrompt: Sentiment Knowledge Enhanced Prompt-Tuning for Aspect-Based Sentiment Analysis

Aspect-based sentiment analysis (ABSA) is an emerging finegrained sentiment analysis task that aims to extract aspects, classify corresponding sentiment polarities and find opinions as the causes of sentiment. The latest research tends to solve the ABSA task in a unified way with end-to-end frameworks. Yet, these frameworks get fine-tuned from downstream tasks without any task-adaptive modification. Specifically, they do not use task-related knowledge well or explicitly model relations between aspect and opinion terms, hindering them from better performance. In this paper, we propose SentiPrompt to use sentiment knowledge enhanced prompts to tune the language model in the unified framework. We inject sentiment knowledge regarding aspects, opinions, and polarities into prompt and explicitly model term relations via constructing consistency and polarity judgment templates from the ground truth triplets. Experimental results demonstrate that our approach can outperform strong baselines on Triplet Extraction, Pair Extraction, and Aspect Term Extraction with Sentiment Classification by a notable margin.

[1]  Xing Xie,et al.  Exploring Sequence-to-Sequence Learning in Aspect Term Extraction , 2019, ACL.

[2]  Tieyun Qian,et al.  Relation-Aware Collaborative Learning for Unified Aspect-Based Sentiment Analysis , 2020, ACL.

[3]  Mark Chen,et al.  Language Models are Few-Shot Learners , 2020, NeurIPS.

[4]  Qing Ling,et al.  Conditional Augmentation for Aspect Term Extraction via Masked Sequence-to-Sequence Generation , 2020, ACL.

[5]  Eduard H. Hovy,et al.  Dual Graph Convolutional Networks for Aspect-based Sentiment Analysis , 2021, ACL.

[6]  Kai Wang,et al.  Relational Graph Attention Network for Aspect-based Sentiment Analysis , 2020, ACL.

[7]  Huajun Chen,et al.  Interventional Aspect-Based Sentiment Analysis , 2021, ArXiv.

[8]  Huajun Chen,et al.  LightNER: A Lightweight Generative Framework with Prompt-guided Attention for Low-resource NER , 2021, ArXiv.

[9]  Franck Dernoncourt,et al.  Introducing Syntactic Structures into Target Opinion Word Extraction with Deep Learning , 2020, EMNLP.

[10]  Graham Neubig,et al.  How Can We Know What Language Models Know? , 2019, Transactions of the Association for Computational Linguistics.

[11]  Jonathan Berant,et al.  oLMpics-On What Language Model Pre-training Captures , 2019, Transactions of the Association for Computational Linguistics.

[12]  Luo Si,et al.  Knowing What, How and Why: A Near Complete Solution for Aspect-based Sentiment Analysis , 2019, AAAI.

[13]  Sebastian Riedel,et al.  Language Models as Knowledge Bases? , 2019, EMNLP.

[14]  Lidong Bing,et al.  Learning Span-Level Interactions for Aspect Sentiment Triplet Extraction , 2021, ACL.

[15]  Zhen Wu,et al.  Latent Opinions Transfer Network for Target-Oriented Opinion Words Extraction , 2020, AAAI.

[16]  Sinno Jialin Pan,et al.  Recursive Neural Structural Correspondence Network for Cross-domain Aspect and Opinion Co-Extraction , 2018, ACL.

[17]  Xin Li,et al.  Aspect Term Extraction with History Attention and Selective Transformation , 2018, IJCAI.

[18]  Fei Huang,et al.  AdaPrompt: Adaptive Prompt-based Finetuning for Relation Extraction , 2021 .

[19]  Zhengxiao Du,et al.  GPT Understands, Too , 2021, AI Open.

[20]  Zhiyang Teng,et al.  Inducing Target-specific Latent Structures for Aspect Sentiment Classification , 2020, EMNLP.

[21]  Lu Xu,et al.  Position-Aware Tagging for Aspect Sentiment Triplet Extraction , 2020, EMNLP.

[22]  Omer Levy,et al.  BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension , 2019, ACL.

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

[24]  Huajun Chen,et al.  Drop Redundant, Shrink Irrelevant: Selective Knowledge Injection for Language Pretraining , 2021, IJCAI.

[25]  Yi Shen,et al.  A Joint Training Dual-MRC Framework for Aspect Based Sentiment Analysis , 2021, AAAI.

[26]  Huajun Chen,et al.  Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners , 2021, ArXiv.

[27]  Xipeng Qiu,et al.  A Unified Generative Framework for Aspect-based Sentiment Analysis , 2021, ACL.

[28]  Yu Wang,et al.  Bidirectional Machine Reading Comprehension for Aspect Sentiment Triplet Extraction , 2021, AAAI.

[29]  Hwee Tou Ng,et al.  An Interactive Multi-Task Learning Network for End-to-End Aspect-Based Sentiment Analysis , 2019, ACL.

[30]  Alexander M. Rush,et al.  Commonsense Knowledge Mining from Pretrained Models , 2019, EMNLP.

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

[32]  Zhiyuan Liu,et al.  PTR: Prompt Tuning with Rules for Text Classification , 2021, AI Open.

[33]  Xinyu Dai,et al.  Grid Tagging Scheme for End-to-End Fine-grained Opinion Extraction , 2020, FINDINGS.

[34]  Percy Liang,et al.  Prefix-Tuning: Optimizing Continuous Prompts for Generation , 2021, ACL.

[35]  Maosong Sun,et al.  Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classification , 2021, ArXiv.

[36]  Danqi Chen,et al.  Making Pre-trained Language Models Better Few-shot Learners , 2021, ACL/IJCNLP.

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

[38]  Huajun Chen,et al.  AliCG: Fine-grained and Evolvable Conceptual Graph Construction for Semantic Search at Alibaba , 2021, KDD.

[39]  Zhen Wu,et al.  Target-oriented Opinion Words Extraction with Target-fused Neural Sequence Labeling , 2019, NAACL.

[40]  Navdeep Jaitly,et al.  Pointer Networks , 2015, NIPS.

[41]  Chenliang Li,et al.  Dependency Graph Enhanced Dual-transformer Structure for Aspect-based Sentiment Classification , 2020, ACL.