Papers by Suyuan Wang

2 papers
E-Gen: Leveraging E-Graphs to Improve Continuous Representations of Symbolic Expressions (2025.naacl-long)

Copied to clipboard

Challenge: Existing methods for embedding mathematical expressions are limited by the size and diversity of training data.
Approach: They propose an e-graph-based dataset generation scheme that synthesizes large and diverse datasets.
Outcome: The proposed method outperforms state-of-the-art large language models on several tasks.
MaRF: Leveraging Representation-Level Fusion of Formula Semantics for Mathematical Information Retrieval (2026.findings-acl)

Copied to clipboard

Challenge: Mathematical information retrieval (MIR) relies on combining textual content with mathematical expressions.
Approach: They propose a dual-encoder representation-level fusion framework for MIR that integrates formula semantics into context-aware dense retrieval.
Outcome: The proposed framework outperforms baselines on the ARQMath-3 benchmark.

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