The problem of thematic indexing of Open Educational Resources (OERs) is often a time-consuming and costly manual task, relying on expert knowledge. In addition, a lot of online resources may be poorly annotated with arbitrary, ad-hoc keywords instead of standard, controlled vocabularies, a fact that stretches up the search space and hampers interoperability. In this paper, we propose an approach that facilitates curators and instructors to annotate thematically educational content. To achieve this, we combine explicit knowledge graph representations with vector-based learning of formal thesaurus terms. We apply this technique in the domain of biomedical literature and show that it is possible to produce a reasonable set of thematic suggestions which exceed a certain similarity threshold. Our method yields acceptable levels for precision and recall against corpora already indexed by human experts. Ordering of recommendations is significant and this approach can also have satisfactory results for the ranking problem. However, traditional IR metrics may not be adequate due to semantic relations amongst recommended terms being underutilized.
The special nature, volume and broadness of biomedical literature pose barriers for automated classification methods. On the other hand, manually indexing is time-consuming, costly and error prone. We argue that current word embedding algorithms can be efficiently used to support the task of biomedical text classification even in a multilabel setting, with many distinct labels. The ontology representation of Medical Subject Headings provides machine-readable labels and specifies the dimensionality of the problem space. Both deep- and shallow network approaches are implemented. Predictions are determined by the similarity between extracted features from contextualized representations of abstracts and headings. The addition of a separate classifier for transfer learning is also proposed and evaluated. Large datasets of biomedical citations are harvested for their metadata and used for training and testing. These automated approaches are still far from entirely substituting human experts, yet they can be useful as a mechanism for validation and recommendation. Dataset balancing, distributed processing and training parallelization in GPUs, all play an important part regarding the effectiveness and performance of proposed methods.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.