Neural Wikipedian: Generating Textual Summaries from Knowledge Base Triples

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Vougiouklis, Pavlos, Elsahar, Hady, Kaffee, Lucie-Aimée, Gravier, Christoph, Laforest, Frederique, Hare, Jonathon, Simperl, Elena
Format: Preprint
Published: 2017
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914856431517696
author Vougiouklis, Pavlos
Elsahar, Hady
Kaffee, Lucie-Aimée
Gravier, Christoph
Laforest, Frederique
Hare, Jonathon
Simperl, Elena
author_facet Vougiouklis, Pavlos
Elsahar, Hady
Kaffee, Lucie-Aimée
Gravier, Christoph
Laforest, Frederique
Hare, Jonathon
Simperl, Elena
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_1711_00155
institution arXiv
publishDate 2017
record_format arxiv
spellingShingle Neural Wikipedian: Generating Textual Summaries from Knowledge Base Triples
Vougiouklis, Pavlos
Elsahar, Hady
Kaffee, Lucie-Aimée
Gravier, Christoph
Laforest, Frederique
Hare, Jonathon
Simperl, Elena
Computation and Language
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.
title Neural Wikipedian: Generating Textual Summaries from Knowledge Base Triples
topic Computation and Language
url https://arxiv.org/abs/1711.00155