TopicEq: A Joint Topic and Mathematical Equation Model for Scientific Texts
arXiv:1902.06034
Abstract
Scientific documents rely on both mathematics and text to communicate ideas. Inspired by the topical correspondence between mathematical equations and word contexts observed in scientific texts, we propose a novel topic model that jointly generates mathematical equations and their surrounding text (TopicEq). Using an extension of the correlated topic model, the context is generated from a mixture of latent topics, and the equation is generated by an RNN that depends on the latent topic activations. To experiment with this model, we create a corpus of 400K equation-context pairs extracted from a range of scientific articles from arXiv, and fit the model using a variational autoencoder approach. Experimental results show that this joint model significantly outperforms existing topic models and equation models for scientific texts. Moreover, we qualitatively show that the model effectively captures the relationship between topics and mathematics, enabling novel applications such as topic-aware equation generation, equation topic inference, and topic-aware alignment of mathematical symbols and words.
arXiv commentAAAI 2019
References in corpus (10)
- Auto-Encoding Variational Bayes
- On the difficulty of training Recurrent Neural Networks
- Exploring the Limits of Language Modeling
- Discovering Discrete Latent Topics with Neural Variational Inference
- A Neural Knowledge Language Model
- Topic Compositional Neural Language Model
- Mathematical Language Processing Project
- Mathematical Language Processing: Automatic Grading and Feedback for Open Response Mathematical Questions
- Factored Temporal Sigmoid Belief Networks for Sequence Learning
- Equation Embeddings