Describing a Knowledge Base
This work addresses the challenge of making knowledge bases more accessible through natural language generation, but it is incremental as it builds on existing pointer network frameworks with specific enhancements.
The paper tackles the problem of automatically generating natural language descriptions from structured knowledge bases, using a pointer network with novel attention mechanisms, and reports that their approach significantly outperforms state-of-the-art methods with reconstructed KB F-scores of 68.8% to 72.6%.
We aim to automatically generate natural language descriptions about an input structured knowledge base (KB). We build our generation framework based on a pointer network which can copy facts from the input KB, and add two attention mechanisms: (i) slot-aware attention to capture the association between a slot type and its corresponding slot value; and (ii) a new \emph{table position self-attention} to capture the inter-dependencies among related slots. For evaluation, besides standard metrics including BLEU, METEOR, and ROUGE, we propose a KB reconstruction based metric by extracting a KB from the generation output and comparing it with the input KB. We also create a new data set which includes 106,216 pairs of structured KBs and their corresponding natural language descriptions for two distinct entity types. Experiments show that our approach significantly outperforms state-of-the-art methods. The reconstructed KB achieves 68.8% - 72.6% F-score.