Syntax Meets Semantics: Understanding Scientific Formulae

• URL: http://arxiv.org/abs/2608.02457v1
• Date: Mon, 03 Aug 2026 16:31:06 GMT
• Title: Syntax Meets Semantics: Understanding Scientific Formulae
• Abstract summary: We study cross-modal correspondence between formula syntax and semantics.<n>We find that their native representation spaces exhibit extremely weak observable correspondence.<n>We apply contrastive learning to induce a shared representation space.
• Score: 2.2549386819889734
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: 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.

Related papers

• Implicit Semantic-Aware Communication Based on Hypergraph Reasoning [37.08230650074803]
  This paper proposes a novel hypergraph-based implicit semantic reasoning framework, HISR, to represent complex multi-entity relationships among semantic knowledge entities.<n> Numerical results show that the proposed HISR achieves up to a 36.6% improvement in implicit semantic interpretation accuracy over the state-of-the-art benchmarks.
  arXiv  Detail & Related papers  (2026-06-18T12:28:30Z)
• Enhancing Pre-trained Representation Classifiability can Boost its Interpretability [112.296393156262]
  We quantify the representation interpretability by leveraging its correlation with the ratio of interpretable semantics within the representations.<n>We propose the Inherent Interpretability Score (IIS) that evaluates the information loss, measures the ratio of interpretable semantics, and quantifies the representation interpretability.
  arXiv  Detail & Related papers  (2025-10-28T06:21:06Z)
• Learning Visual-Semantic Subspace Representations [49.17165360280794]
  We introduce a nuclear norm-based loss function, grounded in the same information theoretic principles that have proved effective in self-supervised learning.<n>We present a theoretical characterization of this loss, demonstrating that, in addition to promoting classity, it encodes the spectral geometry of the data within a subspace lattice.
  arXiv  Detail & Related papers  (2024-05-25T12:51:38Z)
• Neural Semantic Parsing with Extremely Rich Symbolic Meaning Representations [7.774674200374255]
  We introduce a novel compositional symbolic representation for concepts based on their position in the taxonomical hierarchy. This representation provides richer semantic information and enhances interpretability. Our experimental findings demonstrate that the taxonomical model, trained on much richer and complex meaning representations, is slightly subordinate in performance to the traditional model using the standard metrics for evaluation, but outperforms it when dealing with out-of-vocabulary concepts.
  arXiv  Detail & Related papers  (2024-04-19T08:06:01Z)
• How Well Do Text Embedding Models Understand Syntax? [50.440590035493074]
  The ability of text embedding models to generalize across a wide range of syntactic contexts remains under-explored. Our findings reveal that existing text embedding models have not sufficiently addressed these syntactic understanding challenges. We propose strategies to augment the generalization ability of text embedding models in diverse syntactic scenarios.
  arXiv  Detail & Related papers  (2023-11-14T08:51:00Z)
• Prompt-based Logical Semantics Enhancement for Implicit Discourse Relation Recognition [4.7938839332508945]
  We propose a Prompt-based Logical Semantics Enhancement (PLSE) method for Implicit Discourse Relation Recognition (IDRR) Our method seamlessly injects knowledge relevant to discourse relation into pre-trained language models through prompt-based connective prediction. Experimental results on PDTB 2.0 and CoNLL16 datasets demonstrate that our method achieves outstanding and consistent performance against the current state-of-the-art models.
  arXiv  Detail & Related papers  (2023-11-01T08:38:08Z)
• Variational Cross-Graph Reasoning and Adaptive Structured Semantics Learning for Compositional Temporal Grounding [143.5927158318524]
  Temporal grounding is the task of locating a specific segment from an untrimmed video according to a query sentence. We introduce a new Compositional Temporal Grounding task and construct two new dataset splits. We argue that the inherent structured semantics inside the videos and language is the crucial factor to achieve compositional generalization.
  arXiv  Detail & Related papers  (2023-01-22T08:02:23Z)
• On Neural Architecture Inductive Biases for Relational Tasks [76.18938462270503]
  We introduce a simple architecture based on similarity-distribution scores which we name Compositional Network generalization (CoRelNet) We find that simple architectural choices can outperform existing models in out-of-distribution generalizations.
  arXiv  Detail & Related papers  (2022-06-09T16:24:01Z)
• Imposing Relation Structure in Language-Model Embeddings Using Contrastive Learning [30.00047118880045]
  We propose a novel contrastive learning framework that trains sentence embeddings to encode the relations in a graph structure. The resulting relation-aware sentence embeddings achieve state-of-the-art results on the relation extraction task.
  arXiv  Detail & Related papers  (2021-09-02T10:58:27Z)
• Prototypical Representation Learning for Relation Extraction [56.501332067073065]
  This paper aims to learn predictive, interpretable, and robust relation representations from distantly-labeled data. We learn prototypes for each relation from contextual information to best explore the intrinsic semantics of relations. Results on several relation learning tasks show that our model significantly outperforms the previous state-of-the-art relational models.
  arXiv  Detail & Related papers  (2021-03-22T08:11:43Z)
• Logic-guided Semantic Representation Learning for Zero-Shot Relation Classification [31.887770824130957]
  We propose a novel logic-guided semantic representation learning model for zero-shot relation classification. Our approach builds connections between seen and unseen relations via implicit and explicit semantic representations with knowledge graph embeddings and logic rules.
  arXiv  Detail & Related papers  (2020-10-30T04:30:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.