Lune

ACL Findings2024

SenticVec: Toward Robust and Human-Centric Neurosymbolic Sentiment Analysis

Xulang Zhang, Rui Mao, Erik Cambria

Abstract

Recent developments in natural language processing were enabled by deep neural networks, which excel in various tasks through strong data fitting and latent feature modeling abilities. However, certain challenges linked to deep nets and supervised deep learning deserve considerations, e.g., extensive computing resources, knowledge forgetting, etc. Previous research attempted to tackle these challenges individually through irrelative techniques. However, they do not instigate fundamental shifts in the learning paradigm. In this work, we propose a novel neurosymbolic method for sentiment analysis to tackle these issues. We also propose a novel sentiment-pragmatic knowledge base that places emphasis on human subjectivity within varying domain annotations. We conducted extensive experiments to show that our neurosymbolic framework for sentiment analysis stands out for its lightweight nature, robustness across domains and languages, efficient few-shot training, and rapid convergence.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

Builds onCited byLeft to right by year; the more cited, the higher.

Builds on5

  1. Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
  2. Overfitting in adversarially robust deep learningLeslie Rice, Eric Wong, J. Zico KolterICML 2020 · 935 citations
  3. Unsupervised Cross-lingual Representation Learning at ScaleAlexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary et al.ACL 2020 · 539 citations
  4. Effect of scale on catastrophic forgetting in neural networksVinay Venkatesh Ramasesh, Aitor Lewkowycz, Ethan DyerICLR 2022 · 212 citations
  5. Finding the Pillars of Strength for Multi-Head AttentionJinjie Ni, Rui Mao, Zonglin Yang, Han Lei et al.ACL 2023 · 9 citations

Related papers

  1. Neuro-Symbolic Sentiment Analysis with Dynamic Word Sense DisambiguationXulang Zhang, Rui Mao, Kai He, Erik CambriaEMNLP Findings 2023 · 19 citations
  2. Mitigating Neuro-Symbolic Reasoning Shortcuts with Data-Driven Knowledge AugmentationYu-Feng Li, Xiao-Wen Yang, Wen-Da Wei, Jie-Jing Shao et al.KDD 2026
  3. Zero-shot Approach to Overcome Perturbation Sensitivity of PromptsMohna Chakraborty, Adithya Kulkarni, Qi LiACL 2023 · 6 citations
  4. Continual Few-Shot Learning for Text ClassificationRamakanth Pasunuru, Veselin Stoyanov, Mohit BansalEMNLP 2021
  5. Progressive Sentiment Analysis for Code-Switched Text DataSudhanshu Ranjan, Dheeraj Mekala, Jingbo ShangEMNLP Findings 2022 · 2 citations
Dusk over the sea between two cliffs drawn in fine vertical lines