Architectures for natural language generation: Problems and perspectives

Smedt, Koenraad De; Horacek, Helmut; Zock, Michael

doi:10.1007/3-540-60800-1_22

Cited by 20 publications

(15 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This criticism is not the only one against RST. This discourse framework has already been criticized in the generation community (de Smedt et al, 1996). So we advocate the use of SDRT.…”

Section: Comparison With Rstmentioning

confidence: 96%

Document structuring à la SDRT

Danlos¹,

Gaiffe²,

Roussarie³

2001

Proceedings of the 8th European Workshop on Natural Language Generation - EWNLG '01

View full text Add to dashboard Cite

show abstract

“…This criticism is not the only one against RST. This discourse framework has already been criticized in the generation community (de Smedt et al, 1996). So we advocate the use of SDRT.…”

Section: Comparison With Rstmentioning

confidence: 96%

Document structuring à la SDRT

Danlos¹,

Gaiffe²,

Roussarie³

2001

Proceedings of the 8th European Workshop on Natural Language Generation - EWNLG '01

View full text Add to dashboard Cite

show abstract

“…As most of the earlier developed NLG systems adhered to this, it is considered that pipeline architecture is the consensus architecture that can be easily and effectively utilized for language generation tasks [73]. There are quite significant Table 1 shows the list of these tasks categorized under three main modules in pipeline architecture.…”

Section: Pipeline Architecturementioning

confidence: 99%

Recent Advances in Natural Language Generation: A Survey and Classification of the Empirical Literature

Perera

Nand

2017

cai

View full text Add to dashboard Cite

Abstract. Natural Language Generation (NLG) is defined as the systematic approach for producing human understandable natural language text based on nontextual data or from meaning representations. This is a significant area which empowers human-computer interaction. It has also given rise to a variety of theoretical as well as empirical approaches. This paper intends to provide a detailed overview and a classification of the state-of-the-art approaches in Natural Language Generation. The paper explores NLG architectures and tasks classed under document planning, micro-planning and surface realization modules. Additionally, this paper also identifies the gaps existing in the NLG research which require further work in order to make NLG a widely usable technology.

show abstract

“…Of course, it has long been argued that neither natural language understanding nor its counterpart, natural language generation, should be seen as strictly pipeline processes from larger-scale to smaller-scale structures (de Smedt et al, 1996). There are certainly interesting interplays between large scale argument structure and lexical choice, to take just one example (Reed, 1999).…”

Section: Argument Reconstruction: Presuppositions and Stagesmentioning

confidence: 99%

Modelling argument recognition and reconstruction

Katzav

Reed

2008

Journal of Pragmatics

View full text Add to dashboard Cite

A growing body of recent work in informal logic investigates the process of argumentation. Among other things, this work focuses on the ways in which individuals attempt to understand written or verbalised arguments in light of the fact that these are often presented in forms that are incomplete and unmarked. One of its aims is to develop general procedures for natural language argument recognition and reconstruction. Our aim here is to draw on this growing body of knowledge in informal logic in order to take preliminary steps towards developing an architecture for computer systems that are able to recognise and reconstruct natural language arguments. This architecture aims to structure research of an applied and computational nature that strives to implement linguistic systems of various sorts, and to analyse problems in a way that both yields manageable and relatively independent components and also highlights how implementations can interact with existing resources from natural language processing.

show abstract

Architectures for natural language generation: Problems and perspectives

Cited by 20 publications

References 64 publications

Document structuring à la SDRT

Document structuring à la SDRT

Recent Advances in Natural Language Generation: A Survey and Classification of the Empirical Literature

Modelling argument recognition and reconstruction

Contact Info

Product

Resources

About