SciBERT

AbstractObtaining large-scale annotated data for NLP tasks in the scientific domain is challenging and expensive. We release SciBERT, a pretrained language model based on BERT (Devlin et. al., 2018) to …...

AbstractIn specific domains, such as procedural scientific text, human labeled data for shallow semantic parsing is especially limited and expensive to create. Fortunately, such specific domains often use rather formulaic …...

AbstractTraditional document similarity measures provide a coarse-grained distinction between similar and dissimilar documents. Typically, they do not consider in what aspects two documents are similar. This limits the granularity of …...

AbstractScientific keyphrase identification and classification is the task of detecting and classifying keyphrases from scholarly text with their types from a set of predefined classes. This task has a wide …...

AbstractWith worldwide concerns surrounding the Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2), there is a rapidly growing body of scientific literature on the virus. Clinicians, researchers, and policy-makers need to …...

Scientific document understanding is challeng- ing as the data is highly domain specific and diverse. However, datasets for tasks with scien- tific text require expensive manual annotation and tend to …...

AbstractInfusing factual knowledge into pre-trained models is fundamental for many knowledge-intensive tasks. In this paper, we proposed Mixture-of-Partitions (MoP), an infusion approach that can handle a very large knowledge graph …...

AbstractDespite the widespread success of self-supervised learning via masked language models (MLM), accurately capturing fine-grained semantic relationships in the biomedical domain remains a challenge. This is of paramount importance for …...

AbstractThe paper aims to identify cited text spans in the reference paper related to the given citance in the citing paper. We refer to it as cited text span retrieval …...

AbstractThis paper describes our system in the SemEval-2022 Task 12: ‘linking mathematical symbols to their descriptions’, achieving first on the leaderboard for all the subtasks comprising named entity extraction (NER) …...