Linking Theories and Methods in Cognitive Sciences via Joint Embedding of the Scientific Literature: The Example of Cognitive Control
This provides a scalable, unbiased alternative to manual literature reviews for researchers in cognitive sciences, though it is incremental as it applies existing NLP methods to this domain.
The authors tackled the problem of linking theories and methods in cognitive sciences, specifically cognitive control, by creating a joint embedding of tasks and constructs from 385,705 scientific abstracts, enabling automated queries for task batteries and identifying knowledge gaps.
Traditionally, theory and practice of Cognitive Control are linked via literature reviews by human domain experts. This approach, however, is inadequate to track the ever-growing literature. It may also be biased, and yield redundancies and confusion. Here we present an alternative approach. We performed automated text analyses on a large body of scientific texts to create a joint representation of tasks and constructs. More specifically, 385,705 scientific abstracts were first mapped into an embedding space using a transformers-based language model. Document embeddings were then used to identify a task-construct graph embedding that grounds constructs on tasks and supports nuanced meaning of the constructs by taking advantage of constrained random walks in the graph. This joint task-construct graph embedding, can be queried to generate task batteries targeting specific constructs, may reveal knowledge gaps in the literature, and inspire new tasks and novel hypotheses.