Learning to generate one-sentence biographies from Wikidata

Abstract

We investigate the generation of one-sentence Wikipedia biographies from facts derived from Wikidata slot-value pairs. We train a recurrent neural network sequence-to-sequence model with attention to select facts and generate textual summaries. Our model incorporates a novel secondary objective that helps ensure it generates sentences that contain the input facts. The model achieves a BLEU score of 41, improving significantly upon the vanilla sequence-to-sequence model and scoring roughly twice that of a simple template baseline. Human preference evaluation suggests the model is nearly as good as the Wikipedia reference. Manual analysis explores content selection, suggesting the model can trade the ability to infer knowledge against the risk of hallucinating incorrect information.

References in corpus (1)

• A Neural Conversational Model

Cited by in corpus (8)

• Challenges in Data-to-Document Generation
• Describing a Knowledge Base
• Operations Guided Neural Networks for High Fidelity Data-To-Text Generation
• Towards Faithfulness in Open Domain Table-to-text Generation from an Entity-centric View
• Learning to Generate Wikipedia Summaries for Underserved Languages from Wikidata
• Path-based knowledge reasoning with textual semantic information for medical knowledge graph completion
• Architecture for a multilingual Wikipedia
• Neural Entity Summarization with Joint Encoding and Weak Supervision