Sensemaking Networks is a project aiming to address three interrelated limitations of the current science publishing and communication infrastructure: (1) poor reach and feedback, (2) knowledge fragmentation, and (3) rigid formats. To address these …
In contrast to classical cognitive science which studied brains in isolation, ecological approaches focused on the role of the body and environment in shaping cognition. Similarly, in this thesis we adopt an ecological approach to grounded natural …
While open access publishing is effectively broadening *access* to scientific research, the problem of *making sense* of the volumes of new information being published remains at large. Traditional curation methods like peer-reviewed journals are …
Can we teach natural language understanding models to track their beliefs through intermediate points in text? We propose a representation learning framework called breakpoint modeling that allows for learning of this type. Given any text encoder and …
The web has become a dominant epistemic environment, influencing people's beliefs at a global scale. However, online epistemic environments are increasingly polluted, impairing societies' ability to coordinate effectively in the face of global …
While neural language models often perform surprisingly well on natural language understanding (NLU) tasks, their strengths and limitations remain poorly understood. Controlled synthetic tasks are thus an increasingly important resource for …
Large repositories of products, patents and scientific papers offer an opportunity for building systems that scour millions of ideas and help users discover inspirations. However, idea descriptions are typically in the form of unstructured text, …
We develop Process Execution Graphs (PEG), a document-level representation of real-world wet lab biochemistry protocols, addressing challenges such as cross-sentence relations, long-range coreference, grounding, and implicit arguments. We manually …
While natural language understanding (NLU) is advancing rapidly, today's technology differs from human-like language understanding in fundamental ways, notably in its inferior efficiency, interpretability, and generalization. This work proposes an …
Large-scale natural language understanding (NLU) systems have made impressive progress: they can be applied flexibly across a variety of tasks, and employ minimal structural assumptions. However, extensive empirical research has shown this to be a …