mlsanityData to 7 Oct 2026

To be Closer: Learning to Link up Aspects with Opinions

arXiv 2109.08382 ↗First posted 17 Sep 2021cs.CLcited by 5

Not on the map. Why?

Abstract (arXiv)

Dependency parse trees are helpful for discovering the opinion words in aspect-based sentiment analysis (ABSA). However, the trees obtained from off-the-shelf dependency parsers are static, and could be sub-optimal in ABSA. This is because the syntactic trees are not designed for capturing the interactions between opinion words and aspect words. In this work, we aim to shorten the distance between aspects and corresponding opinion words by learning an aspect-centric tree structure. The aspect and opinion words are expected to be closer along such tree structure compared to the standard dependency parse tree. The learning process allows the tree structure to adaptively correlate the aspect and opinion words, enabling us to better identify the polarity in the ABSA task. We conduct experiments on five aspect-based sentiment datasets, and the proposed model significantly outperforms recent strong baselines. Furthermore, our thorough analysis demonstrates the average distance between aspect and opinion words are shortened by at least 19% on the standard SemEval Restaurant14 dataset.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 23 of its 47 references that are in the map. First posted on arXiv 17 Sep 2021.

Builds on

23 of 47 references.

References · 23

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  3. 2020Retrieve, Program, Repeat: Complex Knowledge Base Question Answering via Alternate Meta-learningcited by 216
  4. 2019BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysiscited by 176
  5. 2019Interpretable Neural Predictions with Differentiable Binary Variablescited by 126
  6. 2019Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentencecited by 121
  7. 2020Relational Graph Attention Network for Aspect-based Sentiment Analysiscited by 104
  8. 2020Reasoning with Latent Structure Refinement for Document-Level Relation Extractioncited by 97
  9. 2017Structured Attention Networkscited by 95
  10. 2020Position-Aware Tagging for Aspect Sentiment Triplet Extractioncited by 90
  11. 2016Aspect Level Sentiment Classification with Deep Memory Networkcited by 82
  12. 2018Differentiable Dynamic Programming for Structured Prediction and Attentioncited by 58
11 more
  1. 2018Transformation Networks for Target-Oriented Sentiment Classificationcited by 47
  2. 2019Syntax-Aware Aspect Level Sentiment Classification with Graph Attention Networkscited by 39
  3. 2019Dependency-Guided LSTM-CRF for Named Entity Recognitioncited by 28
  4. 2017Learning Structured Text Representationscited by 24
  5. 2017Jointly Learning Sentence Embeddings and Syntax with Unsupervised Tree-LSTMscited by 23
  6. 2021Better Feature Integration for Named Entity Recognitioncited by 22
  7. 2019Progressive Self-Supervised Attention Learning for Aspect-Level Sentiment Analysiscited by 16
  8. 2018A Tutorial on Deep Latent Variable Models of Natural Languagecited by 10
  9. 2019Quantity Tagger: A Latent-Variable Sequence Labeling Approach to Solving Addition-Subtraction Word Problemscited by 5
  10. 2019Learning Explicit and Implicit Structures for Targeted Sentiment Analysiscited by 5
  11. 2018Towards Dynamic Computation Graphs via Sparse Latent Structurecited by 2

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 2; 2024: 1.

5 papers.

  1. 2022A Survey on Aspect-Based Sentiment Analysis: Tasks, Methods, and Challengescited by 61
  2. 2022DiaASQ : A Benchmark of Conversational Aspect-based Sentiment Quadruple Analysiscited by 27
  3. 2024The Nature of NLP: Analyzing Contributions in NLP Paperscited by 12
  4. 2023Aspect-Based Sentiment Analysis with Explicit Sentiment Augmentationscited by 7
  5. 2023RDGCN: Reinforced Dependency Graph Convolutional Network for Aspect-based Sentiment Analysiscited by 4