Scientific knowledge is predominantly stored in books and scientific journals, often in the form of PDFs. However, the PDF format leads to a loss of semantic information, particularly for mathematical expressions. We propose Nougat (Neural Optical Understanding for Academic Documents), a Visual Transformer model that performs an Optical Character Recognition (OCR) task for processing scientific documents into a markup language, and demonstrate the effectiveness of our model on a new dataset of scientific documents. The proposed approach offers a promising solution to enhance the accessibility of scientific knowledge in the digital age, by bridging the gap between human- readable documents and machine-readable text. We release the models and code to accelerate future work on scientific text recognition.

While recent progress in the field of machine learning (ML) and information retrieval (IR) has been significant, the reproducibility of these cutting-edge results is often lacking, with many submissions failing to provide the necessary information in order to ensure subsequent reproducibility. Despite the introduction of self-check mechanisms before submission (such as the Reproducibility Checklist, criteria for evaluating reproducibility during reviewing at several major conferences, artifact review and badging framework, and dedicated reproducibility tracks and challenges at major IR conferences, the motivation for executing reproducible research is lacking in the broader information community. We propose this tutorial as a gentle introduction to help ensure reproducible research in IR, with a specific emphasis on ML aspects of IR research.

Marcin Kardas, Piotr Czapla, Pontus Stenetorp, Sebastian Ruder, Sebastian Riedel, Ross Taylor, Robert Stojnic. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). 2020.

Inferring the combinatorial regulatory code of transcription factors (TFs) from genome-wide TF binding profiles is challenging. A major reason is that TF binding profiles significantly overlap and are therefore highly correlated. Clustered occurrence of multiple TFs at genomic sites may arise from chromatin accessibility and local cooperation between TFs, or binding sites may simply appear clustered if the profiles are generated from diverse cell populations. Overlaps in TF binding profiles may also result from measurements taken at closely related time intervals. It is thus of great interest to distinguish TFs that directly regulate gene expression from those that are indirectly associated with gene expression. Graphical models, in particular Bayesian networks, provide a powerful mathematical framework to infer different types of dependencies. However, existing methods do not perform well when the features (here: TF binding profiles) are highly correlated, when their association with the biological outcome is weak, and when the sample size is small. Here, we develop a novel computational method, the Neighbourhood Consistent PC (NCPC) algorithms, which deal with these scenarios much more effectively than existing methods do. We further present a novel graphical representation, the Direct Dependence Graph (DDGraph), to better display the complex interactions among variables. NCPC and DDGraph can also be applied to other problems involving highly correlated biological features. Both methods are implemented in the R package ddgraph, available as part of Bioconductor (http://bioconductor.org/packages/2.11/bioc/html/ddgraph.html). Applied to real data, our method identified TFs that specify different classes of cis-regulatory modules (CRMs) in Drosophila mesoderm differentiation. Our analysis also found depletion of the early transcription factor Twist binding at the CRMs regulating expression in visceral and somatic muscle cells at later stages, which suggests a CRM-specific repression mechanism that so far has not been characterised for this class of mesodermal CRMs.