A Machine Learning Pipeline for Automatic Extraction of Statistic Reports and Experimental Conditions from Scientific Papers

We address the problem of extracting reports of statistics along with information about the experimental conditions and topics from scientific publications. A common writing style for statistical results are the recommendations of the American Psychology Association, known as APA-style. However, in practice, writing styles vary as reports are not 100% following APA-style or parameters are not reported despite being mandatory. In addition, the statistics are not reported in isolation but in context of experimental conditions investigated and the general topic. We address these challenges by proposing a flexible pipeline STEREO based on active wrapper induction and unsupervised aspect extraction. Hierarchical active wrapper learning is applied to learn rules to extract the reported statistics. Challenge here is to apply active wrapper on an information extraction task without having formatting landmarks as they can be exploited in HTML pages. Result of step 1 is a set of extracted statistic reports together with sentences in which the reports were found. This is used as input to step 2 of STEREO, which has two two parts. We extract experimental conditions using a grammar-based active wrapper. Furthermore, we identify the experimental topic using an unsupervised attention-based aspect extraction approach adapted to our problem domain. We applied our pipeline to the over 100, 000 documents in the CORD19 dataset. It required only 0.25% of the corpus (about 500 documents) to learn statistics extraction rules that cover 95% of the sentences in CORD-19. The statistic extraction has nearly 100% precision on APA-conform and 95% precision on non-APA writing styles. In total, we were able to extract 113k reported statistics, of which only < 1% is APA conform. We could extract in 46% the correct conditions from APA-conform reports (30% for non-APA). The best model for topic extraction achieves a precision of 75% on statistics reported in APA style (73% for nonAPA conform). We conclude that STEREO is a good foundation for automatic statistic extraction and future developments for scientific paper analysis. Particularly the extraction of non-APA conform reports is important and allows applications such as giving feedback to authors about what is missing and could be changed. Finally, STEREO complements the portfolio of existing metadata extraction tools and can be integrated in a general scientific paper analysis pipeline.