Graph Ensemble Learning over Multiple Dependency Trees for Aspect-level Sentiment Classification

  title={Graph Ensemble Learning over Multiple Dependency Trees for Aspect-level Sentiment Classification},
  author={Xiaochen Hou and Peng Qi and Guangtao Wang and Rex Ying and Jing Huang and Xiaodong He and Bowen Zhou},
Recent work on aspect-level sentiment classification has demonstrated the efficacy of incorporating syntactic structures such as dependency trees with graph neural networks (GNN), but these approaches are usually vulnerable to parsing errors. To better leverage syntactic information in the face of unavoidable errors, we propose a simple yet effective graph ensemble technique, GraphMerge, to make use of the predictions from different parsers. Instead of assigning one set of model parameters to… 

Figures and Tables from this paper

Knowledge Graph Augmented Network Towards Multiview Representation Learning for Aspect-based Sentiment Analysis
A knowledge graph augmented network (KGAN), which aims to effectively incorporate external knowledge with explicitly syntactic and contextual information and proposes a hierarchical fusion module to complement these multiview representations in a local-to-global manner.
Robust Graph Neural Networks via Ensemble Learning
This paper proposes a novel framework of graph ensemble learning based on knowledge passing (called GEL) to address the nonrobustness and oversmoothing issues of GNNs, and designs a multilayer DropNode propagation strategy to reduce each node’s dependence on particular neighbors.
Eliminating Sentiment Bias for Aspect-Level Sentiment Classification with Unsupervised Opinion Extraction
A span- based anti-bias aspect representation learning framework that eliminates the sentiment bias in the aspect embedding by adversarial learning against aspects’ prior sentiment and aligns the distilled opinion candidates with the aspect by span-based dependency modeling to highlight the interpretable opinion terms.
Unified Instance and Knowledge Alignment Pretraining for Aspect-based Sentiment Analysis
This work introduces a unified alignment pretraining framework into the vanilla pretrain-finetune pipeline with both instanceand knowledge-level alignments and introduces a knowledge guidancebased strategy to further bridge the domain gap at the knowledge level.
Self Question-answering: Aspect-based Sentiment Analysis by Role Flipped Machine Reading Comprehension
This paper investigates the ABSA task from the perspective of Machine Reading Comprehension by observing that the aspect and the opinion terms can serve as the query and answer in MRC in-terchangeably, and proposes a new paradigm named Role Flipped Machine Readingcomprehension (RF-MRC) to resolve.
A Survey on Aspect-Based Sentiment Analysis: Tasks, Methods, and Challenges
A new taxonomy for ABSA is provided which organizes existing studies from the axes of concerned sentiment elements, with an emphasis on recent advances of compound ABSA tasks.
Aspect Is Not You Need: No-aspect Differential Sentiment Framework for Aspect-based Sentiment Analysis
This work designs a no-aspect differential sentiment (NADS) framework for the ABSA task, and proposes a differential sentiment loss instead of the cross-entropy loss to better classify the sentiments by distinguishing the different distances between sentiments.
Exploring rich structure information for aspect-based sentiment classification


Aspect-Level Sentiment Analysis Via Convolution over Dependency Tree
A convolution over a dependency tree (CDT) model which exploits a Bi-directional Long Short Term Memory (Bi-LSTM) to learn representations for features of a sentence, and further enhance the embeddings with a graph convolutional network (GCN) which operates directly on the dependency tree of the sentence.
Relational Graph Attention Network for Aspect-based Sentiment Analysis
This paper defines a unified aspect-oriented dependency tree structure rooted at a target aspect by reshaping and pruning an ordinary dependency parse tree and proposes a relational graph attention network (R-GAT) to encode the new tree structure for sentiment prediction.
Aspect-based Sentiment Classification with Aspect-specific Graph Convolutional Networks
This work proposes to build a Graph Convolutional Network (GCN) over the dependency tree of a sentence to exploit syntactical information and word dependencies and raises a novel aspect-specific sentiment classification framework.
Dependency Graph Enhanced Dual-transformer Structure for Aspect-based Sentiment Classification
A dual-transformer structure is devised in DGEDT to support mutual reinforcement between the flat representation learning and graph-based representation learning, and to allow the dependency graph to guide the representation learning of the transformer encoder and vice versa.
Syntax-Aware Aspect Level Sentiment Classification with Graph Attention Networks
A novel target-dependent graph attention network (TD-GAT) is proposed for aspect level sentiment classification, which explicitly utilizes the dependency relationship among words to propagate sentiment features directly from the syntactic context of an aspect target.
Dependency Forest for Sentiment Analysis
A forest-based approach that applies dependency forest to sentiment analysis and develops new algorithms for extracting features from dependency forest, which achieves state-of- the-art performance on the sentiment dataset.
Graph Convolution over Pruned Dependency Trees Improves Relation Extraction
An extension of graph convolutional networks that is tailored for relation extraction, which pools information over arbitrary dependency structures efficiently in parallel is proposed, and a novel pruning strategy is applied to the input trees by keeping words immediately around the shortest path between the two entities among which a relation might hold.
Learning Latent Opinions for Aspect-level Sentiment Classification
A segmentation attention based LSTM model which can effectively capture the structural dependencies between the target and the sentiment expressions with a linear-chain conditional random field (CRF) layer is proposed.
Recurrent Attention Network on Memory for Aspect Sentiment Analysis
We propose a novel framework based on neural networks to identify the sentiment of opinion targets in a comment/review. Our framework adopts multiple-attention mechanism to capture sentiment features
Attentional Encoder Network for Targeted Sentiment Classification
An Attentional Encoder Network (AEN) is proposed for targeted sentiment classification that eschews complex recurrent neural networks and employs attention based encoders for the modeling between context and target, which can excavate the rich introspective and interactive semantic information from the word embeddings without considering the distance between words.