Building applied natural language generation systems

@article{Reiter1997BuildingAN,
  title={Building applied natural language generation systems},
  author={Ehud Reiter and R. Dale},
  journal={Natural Language Engineering},
  year={1997},
  volume={3},
  pages={57 - 87}
}
In this article, we give an overview of Natural Language Generation (NLG) from an applied system-building perspective. The article includes a discussion of when NLG techniques should be used; suggestions for carrying out requirements analyses; and a description of the basic NLG tasks of content determination, discourse planning, sentence aggregation, lexicalization, referring expression generation, and linguistic realisation. Throughout, the emphasis is on established techniques that can be… 

Figures from this paper

Towards Evaluation in Natural Language Generation

TLDR
This paper characterises the NLG task, and in the light of this characterisation a way forward is suggested for evaluation of work in natural language generation that proceeds by looking more closely at the component problems that are addressed in research in the field.

Evaluation in the context of natural language generation

TLDR
What is involved in natural language generation, and how evaluation has figured in work in this area to date is described; a particular text generation application is examined and the issues that are raised in assessing its performance on a variety of dimensions are looked at.

Generating Natural Language Aggregations Using a Propositional Representation of Sets

We present a method for aggregating information from an internal, machine representation and building a text structure that allows us to express aggregations in natural language. Features of the

Instance-Based Natural Language Generation

TLDR
This work develops an efficient search technique for identifying the optimal candidate based on a novel extension of the A* algorithm and details the annotation scheme and grammar induction algorithm and the efficiency and output of the generator.

A System for Automatic English Text Expansion

  • Silvia García-MéndezMilagros Fernández-GavilanesEnrique Costa-MontenegroJonathan Juncal-MartínezFrancisco Javier González-CastañoEhud Reiter
  • Computer Science
    IEEE Access
  • 2019
TLDR
An automatic text expansion system to generate English sentences, which performs automatic Natural Language Generation (NLG) by combining linguistic rules with statistical approaches, which has created the highly precise aLexiE lexicon with wide coverage.

A natural-language paraphrase generator for on-line monitoring and commenting incremental sentence construction by L2 learners of German

TLDR
The grammar formalism of COMPASS-II and its graphical user interface is sketched, and the paraphraser is described and a stepwise demo illustrating the system’s feedback for a sentence under construction is run.

A Constraint-Based Model for Preposition Choice in Natural Language Generation

TLDR
It is shown how a constraint-based approach influences the modelling of preposition lexicalization in natural language generation, allowing to identify all the possible lexical choices which can be predicted from lexical descriptions.

The Sentence Fairy: a natural-language generation system to support children's essay writing

TLDR
An NLP system implementing a ‘virtual writing conference’ for elementary-school children, with German as the target language, is built by deploying natural language generation technology to evaluate and improve the grammatical quality of student output.
...

References

SHOWING 1-10 OF 64 REFERENCES

Aggregation in Natural Language Generation

TLDR
Aggregation, which has been called ellipsis or coordination in Linguistics, is the process that removes redundancies during generation of a natural language discourse, without losing any information.

Current research in natural language generation

TLDR
This book provides a snapshot of the current research in NLG, with particular emphasis on the work conducted by the European research community, and is aimed at an audience already familiar with NLG.

Natural Language Generation Systems

TLDR
VIE-GEN and PHRED are generators for natural language interfaces generating language with a phrasal lexicon and a generator for German texts generation of sentences from a syntactic deep structure with a semantic component.

Knowledge Acquisition for Content Selection

TLDR
These experiments suggest that it is useful to supplement corpus analysis with KA techniques developed for building expert systems, such as structured group discussions and think-aloud protocols, and suspect that in some cases, KA may be easier if other constructive expert-system techniques are used to determine the content of a generated text.

Advances in natural language generation : an interdisciplinary perspective

TLDR
Part 1 Linguistic approaches (in defence of a particular theory, formalism): a phrase-structure grammar with discontinuous grammar, and educational applications: building a sentence generator for teaching linguistics.

Evaluating and comparing three text-production techniques

TLDR
An assessment of three techniques for producing multisentential text: semi-automatic fill-in-the-blank interfacing, automatic linguistic-and-templates hybrid generation, and human writing using a black-box methodology.

Automated Discourse Generation Using Discourse Structure Relations

Lexical Options in Multilingual Generation from a Knowledge Base

TLDR
A more flexible way of attaching lexical items to configurations of concepts and roles, and a lexical option finder that determines the set of content words that cover pieces of the message to be expressed, thereby performing the first half of the “chunking” task.

Generation of Extended Bilingual Statistical Reports

TLDR
The work reported on here concerns the experimental generation of extended bilingual summaries of Canadian statistical data, with a focus on labour force surveys (LFS), where an extensive corpus of published reports in each language is available for empirical study.

A Flexible Interface for Linking Applications to Penman’s Sentence Generator

TLDR
Penman's interface with applications is described, focusing on SPL, a newly developed sentence plan language that can be used by text planning programs to specify plans for sentences at multiple levels of abstraction and varied amounts of detail.
...