Neural Wikipedian: Generating Textual Summaries from Knowledge Base Triples

Abstract

Most people do not interact with Semantic Web data directly. Unless they have the expertise to understand the underlying technology, they need textual or visual interfaces to help them make sense of it. We explore the problem of generating natural language summaries for Semantic Web data. This is non-trivial, especially in an open-domain context. To address this problem, we explore the use of neural networks. Our system encodes the information from a set of triples into a vector of fixed dimensionality and generates a textual summary by conditioning the output on the encoded vector. We train and evaluate our models on two corpora of loosely aligned Wikipedia snippets and DBpedia and Wikidata triples with promising results.

References in corpus (4)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Neural Responding Machine for Short-Text Conversation
• Coverage Embedding Models for Neural Machine Translation

Cited by in corpus (6)

• Toward Subgraph-Guided Knowledge Graph Question Generation with Graph Neural Networks
• Learning to Generate Wikipedia Summaries for Underserved Languages from Wikidata
• Descartes: Generating Short Descriptions of Wikipedia Articles
• WikiTableT: A Large-Scale Data-to-Text Dataset for Generating Wikipedia Article Sections
• End-to-End Learning for Answering Structured Queries Directly over Text
• Generating Titles for Web Tables