Interactive Attention Networks for Aspect-Level Sentiment Classification

@inproceedings{Ma2017InteractiveAN,
  title={Interactive Attention Networks for Aspect-Level Sentiment Classification},
  author={Dehong Ma and Sujian Li and Xiaodong Zhang and Houfeng Wang},
  booktitle={IJCAI},
  year={2017}
}
  • Dehong Ma, Sujian Li, +1 author Houfeng Wang
  • Published in IJCAI 2017
  • Computer Science
  • Aspect-level sentiment classification aims at identifying the sentiment polarity of specific target in its context. Previous approaches have realized the importance of targets in sentiment classification and developed various methods with the goal of precisely modeling their contexts via generating target-specific representations. However, these studies always ignore the separate modeling of targets. In this paper, we argue that both targets and contexts deserve special treatment and need to be… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Explore Further: Topics Discussed in This Paper

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 233 CITATIONS, ESTIMATED 78% COVERAGE

    Effective Attention Networks for Aspect-level Sentiment Classification

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Co-attention Networks for Aspect-Level Sentiment Analysis

    VIEW 3 EXCERPTS
    CITES BACKGROUND
    HIGHLY INFLUENCED

    Effective-target Representation via LSTM with Attention for Aspect-level Sentiment Analysis

    • Quan Liu, Hiroaki Mukaidani
    • Computer Science
    • 2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)
    • 2020
    VIEW 4 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    An Interactive Model of Target and Context for Aspect-Level Sentiment Classification

    VIEW 12 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Interactive Rule Attention Network for Aspect-Level Sentiment Analysis

    VIEW 8 EXCERPTS
    CITES BACKGROUND
    HIGHLY INFLUENCED

    Aspect-based sentiment analysis with alternating coattention networks

    VIEW 4 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    CAN: Constrained Attention Networks for Multi-Aspect Sentiment Analysis

    VIEW 2 EXCERPTS
    CITES METHODS & BACKGROUND

    FILTER CITATIONS BY YEAR

    2018
    2020

    CITATION STATISTICS

    • 63 Highly Influenced Citations

    • Averaged 77 Citations per year from 2018 through 2020

    References

    Publications referenced by this paper.