Papers by Chuan-Ju Wang

7 papers
ESG-KG: A Multi-modal Knowledge Graph System for Automated Compliance Assessment (2026.eacl-demo)

Copied to clipboard

Challenge: Existing methods for ESG compliance assessment rely on fact-based retrieval methods.
Approach: They propose a multi-modal information extraction pipeline to extract, structure, and evaluate sustainability reports.
Outcome: The proposed system extracts, structures, and evaluates ESG-related content from text, tables, figures, and infographics.
A Compare-and-contrast Multistage Pipeline for Uncovering Financial Signals in Financial Reports (2023.acl-long)

Copied to clipboard

Challenge: Recent advances in natural language processing (NLP) have included attempts to efficiently and effectively comprehend lengthy financial documents.
Approach: They propose a signal-highlighting task that analyzes relationships between financial reports . they also create and publicly release a human-annotated dataset for the task .
Outcome: The proposed pipeline is based on a human-annotated dataset and validates its effectiveness.
RiskFinder: A Sentence-level Risk Detector for Financial Reports (N18-5)

Copied to clipboard

Challenge: a web-based information system is proposed for the analysis of financial reports . the system is useful for practitioners and unprecedented among financial academics .
Approach: They propose a web-based information system for facilitating the analyses of financial reports . the system broadens the analyses from the word level to sentence level .
Outcome: The proposed system broadens the analyses from word level to sentence level, making it useful for practitioners and academics.
NASH: Numerically Aware Scoring Heuristic for Robust Semantic Similarity (2026.findings-acl)

Copied to clipboard

Challenge: Numerical precision is critical in financial NLP, yet embedding-based semantic similarity metrics exhibit numerical blindness.
Approach: They propose a model-agnostic metric that decouples numerical verification from textual semantic evaluation.
Outcome: The proposed metric improves numerical sensitivity while maintaining general semantic performance.
MMLF: Multi-query Multi-passage Late Fusion Retrieval (2025.findings-naacl)

Copied to clipboard

Challenge: Existing approaches to query expansion are limited in terms of lexical overlap.
Approach: They propose a query expansion pipeline that generates sub-queries, expands them into pseudo-documents, retrieves them individually and aggregates results using reciprocal rank fusion.
Outcome: The proposed pipeline improves on five BEIR benchmark datasets and achieves a maximum gain of up to 8%.
Designing Templates for Eliciting Commonsense Knowledge from Pretrained Sequence-to-Sequence Models (2020.coling-main)

Copied to clipboard

Challenge: Existing approaches to extract implicit knowledge from pretrained models are still unclear.
Approach: They propose to use a template-based approach to extract implicit knowledge for commonsense reasoning on multiple-choice questions.
Outcome: The proposed template can be extended to other MC tasks with contexts such as supporting facts in open-book question answering settings.
Financial Risk Relation Identification through Dual-view Adaptation (2025.emnlp-main)

Copied to clipboard

Challenge: Identifying inter-firm risk relations is crucial for applications like portfolio management and investment strategy.
Approach: They propose a method for extracting inter-firm risk relations using Form 10-K filings . their method captures implicit and abstract risk connections through unsupervised fine-tuning .
Outcome: The proposed method outperforms baselines across multiple evaluation settings.

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