Neural Wikipedian: Generating Textual Summaries from Knowledge Base Triples
This addresses the need for accessible interfaces to Semantic Web data for non-experts, though it is incremental in applying neural methods to an existing domain.
The paper tackled the problem of generating natural language summaries from Semantic Web data, such as DBpedia and Wikidata triples, using neural networks to encode triples into vectors and produce textual outputs, achieving promising results on aligned Wikipedia snippets.
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.