E-Gen: Leveraging E-Graphs to Improve Continuous Representations of Symbolic Expressions
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915189368029184 |
|---|---|
| author | Zheng, Hongbo Wang, Suyuan Gangwar, Neeraj Kani, Nickvash |
| author_facet | Zheng, Hongbo Wang, Suyuan Gangwar, Neeraj Kani, Nickvash |
| contents | Vector representations have been pivotal in advancing natural language processing (NLP), with prior research focusing on embedding techniques for mathematical expressions using mathematically equivalent formulations. While effective, these approaches are constrained by the size and diversity of training data. In this work, we address these limitations by introducing E-Gen, a novel e-graph-based dataset generation scheme that synthesizes large and diverse mathematical expression datasets, surpassing prior methods in size and operator variety. Leveraging this dataset, we train embedding models using two strategies: (1) generating mathematically equivalent expressions, and (2) contrastive learning to explicitly group equivalent expressions. We evaluate these embeddings on both in-distribution and out-of-distribution mathematical language processing tasks, comparing them against prior methods. Finally, we demonstrate that our embedding-based approach outperforms state-of-the-art large language models (LLMs) on several tasks, underscoring the necessity of optimizing embedding methods for the mathematical data modality. The source code and datasets are available at https://github.com/MLPgroup/E-Gen. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_14951 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | E-Gen: Leveraging E-Graphs to Improve Continuous Representations of Symbolic Expressions Zheng, Hongbo Wang, Suyuan Gangwar, Neeraj Kani, Nickvash Machine Learning Computation and Language Symbolic Computation Vector representations have been pivotal in advancing natural language processing (NLP), with prior research focusing on embedding techniques for mathematical expressions using mathematically equivalent formulations. While effective, these approaches are constrained by the size and diversity of training data. In this work, we address these limitations by introducing E-Gen, a novel e-graph-based dataset generation scheme that synthesizes large and diverse mathematical expression datasets, surpassing prior methods in size and operator variety. Leveraging this dataset, we train embedding models using two strategies: (1) generating mathematically equivalent expressions, and (2) contrastive learning to explicitly group equivalent expressions. We evaluate these embeddings on both in-distribution and out-of-distribution mathematical language processing tasks, comparing them against prior methods. Finally, we demonstrate that our embedding-based approach outperforms state-of-the-art large language models (LLMs) on several tasks, underscoring the necessity of optimizing embedding methods for the mathematical data modality. The source code and datasets are available at https://github.com/MLPgroup/E-Gen. |
| title | E-Gen: Leveraging E-Graphs to Improve Continuous Representations of Symbolic Expressions |
| topic | Machine Learning Computation and Language Symbolic Computation |
| url | https://arxiv.org/abs/2501.14951 |