Content Selection in Data-to-Text Systems: A Survey

Abstract

Data-to-text systems are powerful in generating reports from data automatically and thus they simplify the presentation of complex data. Rather than presenting data using visualisation techniques, data-to-text systems use natural (human) language, which is the most common way for human-human communication. In addition, data-to-text systems can adapt their output content to users' preferences, background or interests and therefore they can be pleasant for users to interact with. Content selection is an important part of every data-to-text system, because it is the module that determines which from the available information should be conveyed to the user. This survey initially introduces the field of data-to-text generation, describes the general data-to-text system architecture and then it reviews the state-of-the-art content selection methods. Finally, it provides recommendations for choosing an approach and discusses opportunities for future research.

References in corpus (5)

• Building Natural-Language Generation Systems
• Individual and Domain Adaptation in Sentence Planning for Dialogue
• Linguistic Descriptions for Automatic Generation of Textual Short-Term Weather Forecasts on Real Prediction Data
• Acquiring Correct Knowledge for Natural Language Generation
• Two-level, Many-Paths Generation

Cited by in corpus (3)

• DART: A Lightweight Quality-Suggestive Data-to-Text Annotation Tool
• Neural Data-to-Text Generation with LM-based Text Augmentation
• Human-like Time Series Summaries via Trend Utility Estimation