Be Concise and Precise: Synthesizing Open-Domain Entity Descriptions from Facts

Abstract

Despite being vast repositories of factual information, cross-domain knowledge graphs, such as Wikidata and the Google Knowledge Graph, only sparsely provide short synoptic descriptions for entities. Such descriptions that briefly identify the most discernible features of an entity provide readers with a near-instantaneous understanding of what kind of entity they are being presented. They can also aid in tasks such as named entity disambiguation, ontological type determination, and answering entity queries. Given the rapidly increasing numbers of entities in knowledge graphs, a fully automated synthesis of succinct textual descriptions from underlying factual information is essential. To this end, we propose a novel fact-to-sequence encoder-decoder model with a suitable copy mechanism to generate concise and precise textual descriptions of entities. In an in-depth evaluation, we demonstrate that our method significantly outperforms state-of-the-art alternatives.

References in corpus (8)

• Neural Machine Translation by Jointly Learning to Align and Translate
• Dynamic Memory Networks for Visual and Textual Question Answering
• End-To-End Memory Networks
• Pointer Sentinel Mixture Models
• Incorporating Copying Mechanism in Sequence-to-Sequence Learning
• A Neural Knowledge Language Model
• CIDEr: Consensus-based Image Description Evaluation
• Video Captioning with Multi-Faceted Attention