Effects of context, complexity, and clustering on evaluation for math formula retrieval
This work addresses the variability in evaluation for math formula retrieval systems, highlighting factors that impact comparisons, but it is incremental as it synthesizes existing test collections without introducing new methods.
The study analyzed six test collections for math formula retrieval, finding that relevance definitions based on context, formula complexity, and clustering by symbol layouts significantly affect system performance and preference ordering.
There are now several test collections for the formula retrieval task, in which a system's goal is to identify useful mathematical formulae to show in response to a query posed as a formula. These test collections differ in query format, query complexity, number of queries, content source, and relevance definition. Comparisons among six formula retrieval test collections illustrate that defining relevance based on query and/or document context can be consequential, that system results vary markedly with formula complexity, and that judging relevance after clustering formulas with identical symbol layouts (i.e., Symbol Layout Trees) can affect system preference ordering.