Building Natural-Language Generation Systems

By Ehud Reiter. 1996

This is a very short paper that briefly discusses some of the tasks that NLG systems perform. It is of no research interest, but I have occasionally found it useful as a way of introducing NLG to potential project collaborators who know nothing about the field.

Subfields: Natural Language Processing

How researchers see this paper

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

In Natural Language Processing

Citations in the corpus

The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics (2021, background): “Natural language generation is the task to automatically generate understandable texts, typically using a non-linguistic or textual representation of information as input (Reiter and Dale, 2000).”
DART: Open-Domain Structured Data Record to Text Generation (2020, background): “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).”
ReferItGame: Referring to Objects in Photographs of Natural Scenes (2014, background): “One common approach is the Incremental Algorithm (Dale and Reiter, 1995; Dale and Reiter, 2000) which uses logical expressions for generation.”
Neural Text Generation from Structured Data with Application to the Biography Domain (2016, background): “Concept-to-text generation renders structured records into natural language (Reiter et al., 2000).”
Sequence-to-Sequence Generation for Spoken Dialogue via Deep Syntax Trees and Strings (2016, background): “It is traditionally divided into two subtasks: sentence planning , which decides on the overall sentence structure, and surface realization , determining the exact word forms and linearizing the structure into a string (Reiter and Dale, 2000).”
What to talk about and how? Selective Generation using LSTMs with Coarse-to-Fine Alignment (2015, background): “Surface realization is often treated as a problem of producing text according to a given representation (Reiter et al., 2000).”
Summarizing Source Code using a Neural Attention Model (2016, background): “Natural language generation has traditionally been addressed as a pipeline of modules that decide ‘what to say’ (content selection) and ‘how to say it’ (realization) separately (Reiter and Dale, 2000; Wong and Mooney, 2007; Chen et al., 2010; Lu and Ng, 2011).”
Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation (2017, methodology): “This characterisation suggests a close similarity to lexicalisation, but Reiter and Dale (2000) point out that the essential difference is that referring expression generation is a ‘discrimination task, where the system needs to communicate sufficient information to distinguish one domain entity…”
Controlling User Perceptions of Linguistic Style: Trainable Generation of Personality Traits (2011, positive): “TheP ERSONAGE architecture (Figure 1) builds on a standard natural language generation (NLG) pipeline architecture as described in Reiter and Dale (2000), Kittredge, Korelsky, and Rambow (1991), and Walker and Rambow (2002).”
Automatic Description Generation from Images: A Survey of Models, Datasets, and Evaluation Measures (2016, background): “Generating text involves a series of steps, traditionally referred to as the NLP pipeline (Reiter & Dale, 2006): we need to decide which aspects of the input to talk about (content selection), then we need to organize the content (text planning) and verbalize it (surface realization).”
Text-to-Text Pre-Training for Data-to-Text Tasks (2020, methodology): “Data-to-Text Early research on data-to-text focused on rule-based methods (Reiter and Dale, 2000), while recent works have favored neural approaches (Wen et al.”
Training a Natural Language Generator From Unaligned Data (2015, methodology): “This corresponds to the sentence planning and surface realization NLG stages as described by Reiter and Dale (2000).”
Data-to-Text Generation with Content Selection and Planning (2018, background): “1 Introduction Data-to-text generation broadly refers to the task of automatically producing text from non-linguistic input (Reiter and Dale 2000; Gatt and Krahmer 2018).”
Individual and Domain Adaptation in Sentence Planning for Dialogue (2007, methodology): “We discuss related work on adaptation in generation using the standard generation architecture which contains modules for content planning (Section 2.1), sentence planning (Section 2.2) and surface realization (Section 2.3) (Kittredge, Korelsky, & Rambow, 1991; Reiter & Dale, 2000).”
Generating Text from Structured Data with Application to the Biography Domain (2016, background): “Concept-to-text generation addresses the problem of rendering structured records into natural language (Reiter et al., 2000).”