An Architecture for Data-to-Text Systems
By Ehud Reiter. 2007
208 citations recorded by the source corpus.
I present an architecture for data-to-text systems, that is NLG systems which produce texts from non-linguistic input data; this essentially extends the architecture of Reiter and Dale (2000) to systems whose input is raw data instead of AI knowledge bases. This architecture is being used in the BabyTalk project, and is based on experiences in several projects at Aberdeen; it also seems to be compatible with many data-to-text systems developed elsewhere. It consists of four stages which are organised in a pipeline: Signal Analysis, Data Interpretation, Document Planning, and Microplanning and Realisation.
Subfields: Artificial Intelligence, Model Architectures, Natural Language Generation
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
- Emiel Krahmer
- Albert Gatt
- Ehud Reiter
- Kees van Deemter
- Anya Belz
- Elizabeth Clark
- Ondrej Dusek
- Mirella Lapata
In Model Architectures
In Natural Language Generation
Citations in the corpus
- DART: Open-Domain Structured Data Record to Text Generation (2020, neutral): “Model Traditional Data-to-Text models break the generation progress into different stages such as signal analysis, data interpretation, document planning, microplanning, and realization (Reiter and Dale, 2000; Reiter, 2007).”
- Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation (2017, methodology): “A more recent development in relation to the pipeline architecture in Figure 3 is a proposal by Reiter (2007) to accommodate systems in which input consists of raw (often numeric) data that requires some preprocessing before it can undergo the kind of selection and planning that the Text Planner is…”
- Evaluation of Text Generation: A Survey (2020, neutral): “, 2019b) and data-to-text generation (Reiter, 2007; Lebret et al., 2016a; Sha et al., 2017; Puduppully et al., 2018; Wang, 2019; Nan et al., 2021).”
- SimpleNLG: A Realisation Engine for Practical Applications (2009, background): “This paper describes SimpleNLG, a realisation engine which grew out of recent experiences in building large-scale data-to-text NLG systems, whose goal is to summarise large volumes of numeric and symbolic data (Reiter, 2007).”