Describing a Knowledge Base
arXiv:1809.01797 · doi:10.18653/v1/W18-6502
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) 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.
arXiv comment12 pages. Accepted by The 11th International Conference on Natural Language Generation (INLG 2018) Code at https://github.com/EagleW/Describing_a_Knowledge_Base
References in corpus (11)
- Neural Machine Translation by Jointly Learning to Align and Translate
- A Structured Self-attentive Sentence Embedding
- Incorporating Copying Mechanism in Sequence-to-Sequence Learning
- Structured Attention Networks
- Bi-Directional Block Self-Attention for Fast and Memory-Efficient Sequence Modeling
- Pointing the Unknown Words
- Challenges in Data-to-Document Generation
- A Graph-to-Sequence Model for AMR-to-Text Generation
- Paper Abstract Writing through Editing Mechanism
- Learning to generate one-sentence biographies from Wikidata
- Learning to Generate Wikipedia Summaries for Underserved Languages from Wikidata
Cited by in corpus (14)
- Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challenge
- PaperRobot: Incremental Draft Generation of Scientific Ideas
- Revisiting Challenges in Data-to-Text Generation with Fact Grounding
- ReviewRobot: Explainable Paper Review Generation based on Knowledge Synthesis
- Variational Template Machine for Data-to-Text Generation
- Learning to Reason for Text Generation from Scientific Tables
- Stage-wise Fine-tuning for Graph-to-Text Generation
- Towards Faithfulness in Open Domain Table-to-text Generation from an Entity-centric View
- Latent Relation Language Models
- WikiTableT: A Large-Scale Data-to-Text Dataset for Generating Wikipedia Article Sections
- Logic-Consistency Text Generation from Semantic Parses
- Linguistic Versus Latent Relations for Modeling Coherent Flow in Paragraphs
- Sketch and Refine: Towards Faithful and Informative Table-to-Text Generation
- An evaluation of template and ML-based generation of user-readable text from a knowledge graph