Neural Wikipedian: Generating Textual Summaries from Knowledge Base Triples

By Pavlos Vougiouklis, Hady ElSahar, Lucie-Aimée Kaffee, Christophe Gravier, Frédérique Laforest, Jonathon S. Hare, Elena Paslaru Bontas Simperl. 2017

70 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Communication, Natural Language Generation, Knowledge Graphs & Representation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Mohit Bansal
2. Caiming Xiong
3. Luke S. Zettlemoyer
4. Hinrich Schütze
5. Percy Liang
6. Richard Socher
7. Graham Neubig
8. Yejin Choi

In Communication

1. Iryna Gurevych
2. Yong Yu
3. Caiming Xiong

In Natural Language Generation

1. Hinrich Schütze
2. Martin Schmitt
3. Rui Zhang
4. Bayu Distiawan Trisedya
5. Jianzhong Qi
6. Leonardo F. R. Ribeiro
7. Iryna Gurevych
8. Rui Zhang

In Knowledge Graphs & Representation

1. Hinrich Schütze
2. Iryna Gurevych
3. Richard Socher
4. Torsten Zesch

Citations in the corpus

• DART: Open-Domain Structured Data Record to Text Generation (2020, background): “Applications include generating sports commentaries (Tanaka-Ishii et al., 1998; Chen and Mooney, 2008; Wiseman et al., 2017; Wang, 2019; Taniguchi et al., 2019), weather forecasts (Goldberg et al., 1994; Reiter et al., 2005; Liang et al., 2009; Konstas and Lapata, 2012; Mei et al., 2016),…”
• Improving Text-to-Text Pre-trained Models for the Graph-to-Text Task (2020, background): “To address this problem, triple-specific or graph-based encoders have been proposed to better process the KG triple input (Vougiouklis et al., 2018; Distiawan et al., 2018; Marcheggiani and Perez-Beltrachini, 2018; Schmitt et al., 2020; Zhao et al., 2020).”
• Investigating Pretrained Language Models for Graph-to-Text Generation (2020, methodology): “…al., 2013; semantic-role labeling, Surdeanu et al., 2008; syntactic and semantic graphs, Belz et al., 2011) and knowledge graphs (KGs) are used to describe factual knowledge in the form of relations between entities (Gardent et al., 2017; Vougiouklis et al., 2018; Koncel-Kedziorski et al., 2019).”
• Triple-to-Text: Converting RDF Triples into High-Quality Natural Languages via Optimizing an Inverse KL Divergence (2019, background): “However, most existing studies focus on the design of the model structure [54], while paying less attention to the training objective.”
• GTR-LSTM: A Triple Encoder for Sentence Generation from RDF Data (2018, methodology): “The most similar system to ours is Neural Wikipedian (Vougiouklis et al., 2017), which generates a summary from RDF triples.”