Papers by Suge Wang

9 papers
SURE: Mutually Visible Objects and Self-generated Candidate Labels For Relation Extraction (2025.coling-main)

Copied to clipboard

Challenge: Joint relation extraction models face high computational complexity, complex network architectures, difficult parameter tuning and limited interpretability.
Approach: They develop a candidate label marker mechanism that prioritizes strategic label selection over simple label generation.
Outcome: The proposed candidate label marks improve the SOTA methods by 2.5%, 1.9%, 1.2% . the proposed candidate labels improve the performance of the proposed methods .
Public Sentiment Drift Analysis Based on Hierarchical Variational Auto-encoder (2020.emnlp-main)

Copied to clipboard

Challenge: Existing methods for detecting public sentiment drift are not designed for sentiment drift detection.
Approach: They propose a Hierarchical Variational Auto-Encoder model to learn better distribution representation and a new drift measure to directly evaluate distribution changes between historical and new data.
Outcome: The proposed model performs better than three existing state-of-the-art methods.
Hierarchical Enhancement Framework for Aspect-based Argument Mining (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing methods have primarily treated ABAM as a nested named entity recognition problem, overlooking the need for tailored strategies to effectively address the specific challenges of ABA M tasks.
Approach: They propose a layer-based Hierarchical Enhancement Framework (HEF) for Aspect-Based Argument Mining and introduce three new components to improve the performance and accuracy.
Outcome: Experiments on multiple datasets and tasks verify the effectiveness of the proposed framework and components.
CVRH: Cross-modal Variational Role Hypergraph Network via Semantic Enhancement for Multi-modal Event Argument Extraction (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods focus on weakly aligning uni-modal representations and generatively data augmentation techniques, but they ignore the potential impact of event role information on MEAE.
Approach: They propose a cross-modal variational role hypergraph network via semantic enhancement to model high-order role correlations among cross-mod arguments in multi-modal documents.
Outcome: The proposed method achieves a 6.9% improvement in F1-score on the M2E2 benchmark compared to current state-of-the-art methods.
Document-Level Event Extraction via Information Interaction Based on Event Relation and Argument Correlation (2024.lrec-main)

Copied to clipboard

Challenge: Document-level Event Extraction (DEE) is a vital task in NLP . current approaches overlook intricate relationships among events and subtle correlations among arguments within a document .
Approach: They propose a document-level event extraction tool that integrates event relationships and argument correlation graphs to model the relationship among events.
Outcome: The proposed network outperforms existing models and large language models in terms of F1-score across two benchmark datasets.
Jointly Identifying Rhetoric and Implicit Emotions via Multi-Task Learning (2021.findings-acl)

Copied to clipboard

Challenge: Experimental results validate the benefit of the proposed model over the state-of-the-art baselines for rhetoric and emotion identification tasks.
Approach: They propose a multi-task learning framework that can encode categorical correlation between tasks to improve rhetoric and emotion identification problem.
Outcome: The proposed model can encode the categorical correlation between tasks to improve rhetoric and emotion identification problem.
Emotion Inference in Multi-Turn Conversations with Addressee-Aware Module and Ensemble Strategy (2021.emnlp-main)

Copied to clipboard

Challenge: Empirical studies on three different benchmark conversation datasets demonstrate the effectiveness of the proposed model over several strong baselines.
Approach: They propose an addressee-aware module to automatically learn whether the participant keeps the historical emotional state or is affected by others in the next upcoming turn.
Outcome: The proposed model can predict the participant's emotion in the next upcoming turn without knowing the participant’s response yet.
Enhancing Event Causality Identification with Event Causal Label and Event Pair Interaction Graph (2023.findings-acl)

Copied to clipboard

Challenge: Existing methods for event causality identification (ECI) do not consider event causal label information and interaction information between event pairs.
Approach: They propose a framework to enrich the representation of event pairs by introducing the event causal label information and the interaction information between event pairs.
Outcome: The proposed framework outperforms state-of-the-art methods on two benchmark datasets.
My Words Imply Your Opinion: Reader Agent-Based Propagation Enhancement for Personalized Implicit Emotion Analysis (2025.acl-long)

Copied to clipboard

Challenge: Current studies personalize emotion analysis by focusing on the author but neglect the impact of the intended reader on implicit emotional feedback.
Approach: They propose a model which incorporates reader feedback into implicit emotion analysis (IEA) they use large language models to create reader agents to simulate reader feedback .
Outcome: The proposed model outperforms state-of-the-art models in a text-centric environment.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations