Neural Wikipedian: Generating Textual Summaries from Knowledge Base Triples

TL;DR

This paper presents a neural network system that generates natural language summaries from Semantic Web triples, enabling easier understanding of complex data for general users.

Contribution

It introduces a neural approach to generate textual summaries from knowledge base triples, addressing the challenge of open-domain data summarization.

Findings

Effective encoding of triples into fixed-dimensional vectors.

Successful generation of summaries from Wikipedia, DBpedia, and Wikidata.

Promising results demonstrating feasibility of neural summarization for Semantic Web data.

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.