Corpus ID: 4303760

Equation Embeddings

  title={Equation Embeddings},
  author={K. Krstovski and D. Blei},
  • K. Krstovski, D. Blei
  • Published 2018
  • Mathematics, Computer Science
  • ArXiv
  • 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… CONTINUE READING
    12 Citations
    TopicEq: A Joint Topic and Mathematical Equation Model for Scientific Texts
    • 6
    • PDF
    Math-word embedding in math search and semantic extraction
    • 2
    • Highly Influenced
    • PDF
    Why Machines Cannot Learn Mathematics, Yet
    • 4
    • PDF
    Premise Selection in Natural Language Mathematical Texts
    • 2
    • PDF
    Towards Grounding of Formulae
    Natural Language Premise Selection: Finding Supporting Statements for Mathematical Text
    • 3
    • PDF
    Automatic Generation of Headlines for Online Math Questions


    Exponential Family Embeddings
    • 83
    • PDF
    Structured Embedding Models for Grouped Data
    • 22
    • PDF
    Glove: Global Vectors for Word Representation
    • 15,457
    • Highly Influential
    • PDF
    Distributed Representations of Words and Phrases and their Compositionality
    • 19,612
    • Highly Influential
    • PDF
    Efficient Estimation of Word Representations in Vector Space
    • 15,687
    • Highly Influential
    • PDF
    Neural Word Embedding as Implicit Matrix Factorization
    • 1,237
    • PDF
    When Are Tree Structures Necessary for Deep Learning of Representations?
    • 184
    • PDF
    Distributed Representations of Sentences and Documents
    • 5,422
    • PDF
    Software Framework for Topic Modelling with Large Corpora
    • 2,725
    • PDF
    Multi-Stage Math Formula Search: Using Appearance-Based Similarity Metrics at Scale
    • 27
    • PDF