Improving Question Answering over Incomplete KBs with Knowledge-Aware Reader
This work addresses the challenge of incomplete knowledge for question answering systems, representing an incremental improvement in the field.
The paper tackles the problem of question answering over incomplete knowledge bases by proposing a model that aggregates evidence from both structured KBs and retrieved text snippets, achieving consistent improvements on the WebQSP benchmark across varying levels of KB incompleteness.
We propose a new end-to-end question answering model, which learns to aggregate answer evidence from an incomplete knowledge base (KB) and a set of retrieved text snippets. Under the assumptions that the structured KB is easier to query and the acquired knowledge can help the understanding of unstructured text, our model first accumulates knowledge of entities from a question-related KB subgraph; then reformulates the question in the latent space and reads the texts with the accumulated entity knowledge at hand. The evidence from KB and texts are finally aggregated to predict answers. On the widely-used KBQA benchmark WebQSP, our model achieves consistent improvements across settings with different extents of KB incompleteness.