Preliminary Exploration of Formula Embedding for Mathematical Information Retrieval: can mathematical formulae be embedded like a natural language?

While neural network approaches are achieving breakthrough performance in the natural language related €elds, there have been few similar aŠempts at mathematical language related tasks. In this study, we explore the potential of applying neural representation techniques to Mathematical Information Retrieval (MIR) tasks. In more detail, we €rst brieƒy analyze the characteristic di‚erences between natural language and mathematical language. Œen we design a “symbol2vec” method to learn the vector representations of formula symbols (numbers, variables, operators, functions, etc.) Finally, we propose a “formula2vec” based MIR approach and evaluate its performance. Preliminary experiment results show that there is a promising potential for applying formula embedding models to mathematical language representation and MIR tasks.