EMNLP Findings2023
Neuro-Symbolic Sentiment Analysis with Dynamic Word Sense Disambiguation
Abstract
Sentiment analysis is a task that highly depends on the understanding of word senses. Traditional neural network models are black boxes that represent word senses as vectors that are uninterpretable for humans. On the other hand, the application of Word Sense Disambiguation (WSD) systems in downstream tasks poses challenges regarding i) which words need to be disambiguated, and ii) how to model explicit word senses into easily understandable terms for a downstream model. This work proposes a neurosymbolic framework that incorporates WSD by identifying and paraphrasing ambiguous words to improve the accuracy of sentiment predictions. The framework allows us to understand which words are paraphrased into which semantically unequivocal words, thus enabling a downstream task model to gain both accuracy and interpretability. To better fine-tune a lexical substitution model for WSD on a downstream task without ground-truth word sense labels, we leverage dynamic rewarding to jointly train sentiment analysis and lexical substitution models. Our framework proves to effectively improve the performance of sentiment analysis on corpora from different domains.
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.
2 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- MADAWSD: Multi-Agent Debate Framework for Adversarial Word Sense Disambiguation cites Breaking Through the 80% Glass Ceiling: Raising the State of the Art in Word Sense Disambiguation by Incorporating Knowledge Graph Information
- WSDPO: A Generative Word Sense Disambiguation Framework with Chain-of-Thought and Preference Optimization cites MADAWSD: Multi-Agent Debate Framework for Adversarial Word Sense Disambiguation
- Improved Word Sense Disambiguation with Enhanced Sense Representations cites Breaking Through the 80% Glass Ceiling: Raising the State of the Art in Word Sense Disambiguation by Incorporating Knowledge Graph Information
- Explainable Metaphor Identification Inspired by Conceptual Metaphor Theory cites Bridging Towers of Multi-task Learning with a Gating Mechanism for Aspect-based Sentiment Analysis and Sequential Metaphor Identification
Cited by top-tier papers2
- MADAWSD: Multi-Agent Debate Framework for Adversarial Word Sense DisambiguationKaiyuan Zhang, Qian Liu, Luyang Zhang, Chaoqun Zheng et al.EMNLP 2025
- WSDPO: A Generative Word Sense Disambiguation Framework with Chain-of-Thought and Preference OptimizationKunpeng Kang, Shuaimin Li, Kaiyuan Zhang, Luyang Zhang et al.ACL 2026
Builds on7
- Deberta: decoding-Enhanced Bert with Disentangled AttentionPengcheng He, Xiaodong Liu, Jianfeng Gao, Weizhu ChenICLR 2021 · 3,729 citations
- Breaking Through the 80% Glass Ceiling: Raising the State of the Art in Word Sense Disambiguation by Incorporating Knowledge Graph InformationMichele Bevilacqua, Roberto NavigliACL 2020 · 145 citations
- Bridging Towers of Multi-task Learning with a Gating Mechanism for Aspect-based Sentiment Analysis and Sequential Metaphor IdentificationRui Mao, Xiao LiAAAI 2021 · 119 citations
- Explainable Metaphor Identification Inspired by Conceptual Metaphor TheoryMengshi Ge, Rui Mao, Erik CambriaAAAI 2022 · 67 citations
- Improved Word Sense Disambiguation with Enhanced Sense RepresentationsYang Song, Xin Cai Ong, Hwee Tou Ng, Qian LinEMNLP Findings 2021 · 29 citations
Related papers
- SenticVec: Toward Robust and Human-Centric Neurosymbolic Sentiment AnalysisXulang Zhang, Rui Mao, Erik CambriaACL Findings 2024 · 16 citations
- Word Sense Linking: Disambiguating Outside the SandboxAndrei Stefan Bejgu, Edoardo Barba, Luigi Procopio, Alberte Fernández-Castro et al.ACL Findings 2024 · 1 citation
- A Synset Relation-enhanced Framework with a Try-again Mechanism for Word Sense DisambiguationMing Wang, Yinglin WangEMNLP 2020 · 29 citations
- SenseBERT: Driving Some Sense into BERTYoav Levine, Barak Lenz, Or Dagan, Ori Ram et al.ACL 2020 · 27 citations
- Improving In-Context Learning with Prediction Feedback for Sentiment AnalysisHongling Xu, Qianlong Wang, Yice Zhang, Min Yang et al.ACL Findings 2024 · 7 citations
