Pith. sign in

REVIEW 5 cited by

Equation Embeddings

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1803.09123 v1 pith:25REZFPN submitted 2018-03-24 stat.ML cs.CLcs.LG

Kriste Krstovski , David M. Blei This is my paper · ORCID
classification stat.MLcs.CLcs.LG
keywords equationsembeddingsequationrepresentationssemanticanalyzefoundfour
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

We present an unsupervised approach for discovering semantic representations of mathematical equations. Equations are challenging to analyze because each is unique, or nearly unique. Our method, which we call equation embeddings, finds good representations of equations by using the representations of their surrounding words. We used equation embeddings to analyze four collections of scientific articles from the arXiv, covering four computer science domains (NLP, IR, AI, and ML) and $\sim$98.5k equations. Quantitatively, we found that equation embeddings provide better models when compared to existing word embedding approaches. Qualitatively, we found that equation embeddings provide coherent semantic representations of equations and can capture semantic similarity to other equations and to words.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Syntax Meets Semantics: Understanding Scientific Formulae

    cs.IR 2026-08 conditional novelty 6.0 of 10

    Formula syntax and textual semantics show weak direct correspondence but strong latent correlation; contrastive learning bridges the gap and lifts retrieval from ~5% to ~58% recall@10.

  2. Exponential Family Attention

    stat.ML 2025-01 reject novelty 6.0 of 10

    EFA sets the natural parameters of exponential family distributions to self-attention-transformed context embeddings, subsuming linear latent factor models and beating them on held-out prediction for several datasets.

  3. E-Gen: Leveraging E-Graphs to Improve Continuous Representations of Symbolic Expressions

    cs.LG 2025-01 conditional novelty 6.0 of 10

    An e-graph-based data generator produces 55 million equivalent-expression training pairs, and embeddings trained on them beat prior math-embedding models and GPT-4o on several symbolic math tasks.

  4. SSEmb: A Joint Structural and Semantic Embedding Framework for Mathematical Formula Retrieval

    cs.IR 2025-08 conditional novelty 5.0 of 10

    SSEmb, which fuses Operator Graph contrastive embeddings with Sentence-BERT text embeddings, reports state-of-the-art contextualized formula retrieval on ARQMath-3.

  5. AI for Mathematics: Progress, Challenges, and Prospects

    math.HO 2026-01 unverdicted novelty 4.0 of 10

    AI for math combines task-specific architectures and general foundation models to support research and advance AI reasoning capabilities.

Pith tools