SimpleNLG: A Realisation Engine for Practical Applications

By Albert Gatt, Ehud Reiter. 2009

436 citations recorded by the source corpus.

This paper describes SimpleNLG, a realisation engine for English which aims to provide simple and robust interfaces to generate syntactic structures and linearise them. The library is also flexible in allowing the use of mixed (canned and non-canned) representations.

Subfields: Artificial Intelligence, 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 Artificial Intelligence

In Natural Language Processing

Citations in the corpus

Neural Generation for Czech: Data and Baselines (2019, methodology): “The procedural SimpleNLG realizer (Gatt and Reiter, 2009) has also been ported into multiple languages (Bollmann, 2011; Vaudry and Lapalme, 2013; de Oliveira and Sripada, 2014; Mazzei et al.”
Choosing Linguistics over Vision to Describe Images (2012, positive): “Though the sentences generated in our case follow a template-like structure, use of SimpleNLG saves the manual effort of writing individual templates.”
Adapting SimpleNLG for Bilingual English-French Realisation (2013, background): “SimpleNLG, as described in Gatt and Reiter (2009), is a realisation engine for English in the form of a Java library.”
Towards coherent natural language description of video streams (2011, positive): “For implementing templates, simpleNLG [5] is used.”
Going Dutch: Creating SimpleNLG-NL (2018, background): “SimpleNLG is a Java-based surface realisation library aimed at practical applications (Gatt and Reiter, 2009).”
SimpleNLG-ZH: a Linguistic Realisation Engine for Mandarin (2018, methodology): “software design paradigm of SimpleNLG (Gatt and Reiter, 2009).”
Natural Language Generation enhances human decision-making with uncertain information (2016, methodology): “Natural Language Generation (NLG) technology can achieve comparable results to commonly used data visualisation techniques for supporting accurate human decision-making (Gatt et al., 2009).”
Using NLG for speech synthesis of mathematical sentences (2019, background): “The results of the experimentation suggests (1) a preference for formant-based synthesizer with respect to NN-based synthesizer, (2) the performances on simple expressions are good, but (3) on more structurally complex expressions need improvements In future work we intend to expand the lexicon in o”
Text Generation with Exemplar-based Adaptive Decoding (2019, neutral): “The encoder-decoder approach differs considerably from earlier template-based meth-∗ ods (Becker, 2002; Foster and White, 2004; Reiter et al., 2005; Gatt and Reiter, 2009, inter alia ), where the source content is ﬁlled into the slots of a handcrafted template.”
Sticking to the Facts: Confident Decoding for Faithful Data-to-Text Generation (2019, neutral): “While traditionally done with template-based approaches (Becker, 2002; Foster & White, 2004; Gatt & Reiter, 2009; Reiter et al., 2005), recently neural encoder-decoder approaches (Sutskever et al., 2014; Cho et al., 2014; Bahdanau et al., 2014) have become a popular approach.”
Human Focused Video Description (2011, methodology): “For implementing the templates, simpleNLG is used [6].”
Adapting SimpleNLG to Galician language (2018, methodology): “This is the case of SimpleNLG, a Java realiser for English presented in (Gatt and Reiter, 2009) to facilitate realisation tasks.”
SimpleNLG-IT: adapting SimpleNLG to Italian (2016, methodology): “the main features of the porting of the SimpleNLG API system (Gatt and Reiter, 2009) to Italian.”
Adapting SimpleNLG to German (2011, background): “SimpleNLG, as described in Gatt and Reiter (2009), is a realisation engine for English that fulﬁlls this description.”
Learning Neural Templates for Text Generation (2018, background): “Traditional NLG systems (Kukich, 1983; McKeown, 1992; Belz, 2008; Gatt and Reiter, 2009), in contrast, largely avoid these problems.”