DIFFERENTIABLE MULTI-HOP REASONING OVER A VIRTUAL KNOWLEDGE BASE

We wish to put forward an approach for accessing text as a knowledge base which is useful for question-answering (QA). This approach relies centrally on development of a differentiable operator which allows us to traverse textual data like a``virtual''KB. The core of the approach is a neural module that inputs and outputs sets of entities: in particular, this module uses maximum inner product search (MIPS) on a special index to map a set of entities to all entities related to something in (by some specified relations), as witnessed by some text in the corpus. For multi-hop questions, the set of output entities can be again used recursively as the input to a second copy of the module, enabling us to answer complex questions. This module is differentiable, so the full system can be trained completely end-to-end using gradient based methods. Thus, we name it DrKIT: Differentiable Reasoning over a virtual Knowledge …