Get to know your neighbors

Natural language underspecifies the information-rich situations that it describes and communicates. For example, the sentence “She pumped her fist” connotes many potential auspicious causes. For machines to understand natural language, they must be able to make commonsense inferences that enrich explicitly stated information. However, current NLP systems lack the ability to ground the situations they read and write about to relevant world knowledge.

Moreover, they struggle to reason over available facts to generalize to future unseen events. In this talk, I will describe efforts at transforming modern language models into commonsense knowledge models by leveraging implicitly encoded knowledge representations. Then, I will discuss work in designing natural language reasoning systems that use knowledge graphs as a structural scaffold for aggregating information across relevant commonsense inferences.