---
title: "语法与语义：理解科学公式的跨模态表示"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2608.02457v1"
permalink: "https://feed.astralor.com/items/itm_02abe418117c181fb1043adc"
published: "2026-08-03T16:31:06.000Z"
score: 76
channel: "ai"
tags: ["对比学习","科学公式","表示学习","跨模态检索"]
---

# 语法与语义：理解科学公式的跨模态表示

## AI 点评

> 这篇论文让我感到兴奋的地方在于，它把公式从“符号串”重新定义为双重模态对象，这对做学术搜索、知识图谱和AI审稿的人尤其有价值。作者给出的对比学习路径非常直接，团队可以马上拿来在现有系统上做验证。

## 速览

科学公式在学术交流中既包含语法结构又承载语义，但两者的关系在学术信息检索中少被系统研究。本论文通过图编码器表示句法、文本编码器表示语义，发现两者原生表示空间对应极弱但潜在相关性显著。利用对比学习对齐表示后，跨模态检索性能大幅提升，表明显式表示学习能恢复原始空间中缺失的对应关系，为科学文献理解和检索提供了新思路。

## 关键点

- 科学公式具有语法与语义双重属性，在检索系统中两者的相关性未被充分利用。
- 实验显示公式句法与语义的原生表示空间对应极弱，但存在强潜在相关性。
- 采用图编码器与文本编码器并应用对比学习，可有效建立共享表示空间。
- 对齐后的跨模态检索性能显著提升，验证了显式表示学习的必要性。

## 全文

Scientific formulae are a fundamental component of scholarly communication, yet their dual nature -- as structured syntax and carriers of semantics -- remains underexplored in scholarly information retrieval. Although prior studies show that jointly modeling syntactic and semantic modalities improves retrieval performance, the relationship between their underlying representations has not been systematically investigated. In this work, we empirically study cross-modal correspondence between formula syntax and semantics. We find that their native representation spaces exhibit extremely weak observable correspondence despite strong latent correlation, indicating a substantial representation mismatch between the two modalities. We further evaluate whether this mismatch can be reduced using standard representation learning and alignment techniques. We represent syntactic structure using graph-based encoders and semantic information using text-based encoders, then apply contrastive learning to induce a shared representation space. Results show that the learned alignment substantially improves cross-modal retrieval, suggesting that explicit representation learning can recover correspondence absent from the original representation spaces.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_02abe418117c181fb1043adc