Challenges in Information Extraction from Tables in Biomedical Research Publications: a Dataset Analysis

We present a study of a dataset of tables from biomedical research publications. Our aim is to identify characteristics of biomedical tables that pose challenges for the task of extracting information from tables, and to determine which parts of research papers typically contain information that is useful for this task. Our results indicate that biomedical tables are hard to interpret without their source papers due to the brevity of the entries in the tables. In many cases, unstructured text segments, such as table titles, footnotes and non-table prose discussing a table, are required to interpret the table’s entries.