@inproceedings{wang-etal-2018-describing,
    title = "Describing a Knowledge Base",
    author = "Wang, Qingyun  and
      Pan, Xiaoman  and
      Huang, Lifu  and
      Zhang, Boliang  and
      Jiang, Zhiying  and
      Ji, Heng  and
      Knight, Kevin",
    editor = "Krahmer, Emiel  and
      Gatt, Albert  and
      Goudbeek, Martijn",
    booktitle = "Proceedings of the 11th International Conference on Natural Language Generation",
    month = nov,
    year = "2018",
    address = "Tilburg University, The Netherlands",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/W18-6502",
    doi = "10.18653/v1/W18-6502",
    pages = "10--21",
    abstract = "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) \textit{slot-aware attention} to capture the association between a slot type and its corresponding slot value; and (ii) a new \textit{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 \textit{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.",
}