Academia.eduAcademia.edu

Outline

Title
Abstract
References

Natural Language Generation

Profile image of Michael ZockMichael Zock

2005, Oxford Handbooks Online

https://doi.org/10.1093/OXFORDHB/9780199276349.013.0015
visibility

…

description

21 pages

link

1 file

Abstract

Communication via a natural language requires two fundamental skills, producing 'text' (written or spoken) and understanding it. Th is chapter introduces newcomers to the fi eld of computational approaches to the former-natural language generation (henceforth NLG)-showing some of the theoretical and practical problems that linguists, computer scientists, and psychologists have encountered when trying to explain how language works in machines or in our minds. ¹ Authors in alphabetical order     . G I: W  N L G (C, L,  S D)

Related papers

Introduction to the special issue on natural language generation
Robert Dale, Donia Scott, Barbara Di Eugenio

Computational Linguistics, 1998

View PDFchevron_right
Current Research in Natural Language Generation
Robert Dale

Language, 1992

View PDFchevron_right
Acquiring Correct Knowledge for Natural Language Generation
Rig Hunter

Journal of Artificial Intelligence Research, 2003

Natural language generation (nlg) systems are computer software systems that produce texts in English and other human languages, often from non-linguistic input data. nlg systems, like most ai systems, need substantial amounts of knowledge. However, our experience in two nlg projects suggests that it is difficult to acquire correct knowledge for nlg systems; indeed, every knowledge acquisition (ka) technique we tried had significant problems. In general terms, these problems were due to the complexity, novelty, and poorly understood nature of the tasks our systems attempted, and were worsened by the fact that people write so differently. This meant in particular that corpus-based ka approaches suffered because it was impossible to assemble a sizable corpus of high-quality consistent manually written texts in our domains; and structured expert-oriented ka techniques suffered because experts disagreed and because we could not get enough information about special and unusual cases to build robust systems. We believe that such problems are likely to affect many other nlg systems as well. In the long term, we hope that new ka techniques may emerge to help nlg system builders. In the shorter term, we believe that understanding how individual ka techniques can fail, and using a mixture of different ka techniques with different strengths and weaknesses, can help developers acquire nlg knowledge that is mostly correct.

View PDFchevron_right
Preliminary report on a program for generating natural language
David McDonald

International Joint Conference on Artificial Intelligence, 1975

A program framework has bben designed in which the lingLuistic facts and heuristics necessary for generating fluent natural language can be encoded. The linguistic data is represented in annotated procedures and data structures which are designed to make English translations of already formulated messages given:in a primary program's internal representation. The messages must include the program's intentions in saying them, in order to adequately specify the grammatical operations required for a translatibn. The pertinant questions in this research have been,: what structure does natural language have that allows it to encode mutifaceted messages; and how must that structure be taken into account in the design of a generation facility for a computer.program. This paper describes the control and data structures of the design and and their motivation. It is a condensation of my Master's Thesis <1>, to which the reader is refered for further information. Work is presently underway on implementing the design in LISP and developing a grammar for use in one or more'of the domains given below.

View PDFchevron_right
Design issues in building natural language generators
Mark Maybury

7th Computers in Aerospace Conference, 1989

This paper outlines some key issues concerning the design of a natural language generation component for knowledge based systems. These ideas arise from research completed at Rome Air Development Center with the purpose of producing cohesive English text from the Knowledge Replanning System (KRS) [Dawson et al, 19871, an expert system which produces air tasking orders for offensive counter air missions. Desired characteristics of generators include (1) independence from both domain and knowledge formalism and potentially from language, (2) flexibility and scope of linguistic formalisn;s, and (3) adaptability to the type and attributes of the user.

View PDFchevron_right
Towards a Reference Architecture for Natural Language Generation Systems
Lynne Cahill

1999

We present the rags (Reference Architecture for Generation Systems) framework: a specification of an abstract Natural Language Generation (NLG) system architecture to support sharing, re-use, comparison and evaluation of NLG technologies. We argue that the evidence from a survey of actual NLG systems calls for a different emphasis in a reference proposal from that seen in similar initiatives in information extraction and multimedia interfaces. We introduce the framework itself, in particular the two-level data model that allows us to support the complex data requirements of NLG systems in a flexible and coherent fashion, and describe our efforts to validate the framework through a range of implementations.

View PDFchevron_right
doi: 10.1017/S1351324906004104 Printed in the United Kingdom A Reference Architecture for Natural Language Generation Systems∗
Mike Reape

2004

We present the rags (Reference Architecture for Generation Systems) framework: a specification of an abstract Natural Language Generation (NLG) system architecture to support sharing, re-use, comparison and evaluation of NLG technologies. We argue that the evidence from a survey of actual NLG systems calls for a different emphasis in a reference proposal from that seen in similar initiatives in information extraction and multimedia interfaces. We introduce the framework itself, in particular the two-level data model that allows us to support the complex data requirements of NLG systems in a flexible and coherent fashion, and describe our efforts to validate the framework through a range of implementations. * This is a revised and updated version of the paper "A Reference Architecture for Generation Systems" which appeared (in error) in Natural Language Engineering 10(3/4) the Special Issue on Software Architectures for Language Engineering. This version should be cited in preference to the earlier one. 1 This survey drew on Reiter's original (Reiter 1994) formulation of the model. The later (Reiter and Dale 2000) formulation uses slightly different terminology, which we also use here, but for our purposes is otherwise not significantly different. 2 The systems surveyed were:

View PDFchevron_right
Handbook for language engineers
Ali Farghaly

2003

View PDFchevron_right
Proceedings of the 12th European Workshop on Natural Language Generation (ENLG 2009)}
Albert Gatt

2009

View PDFchevron_right
Has a Consensus NL Generation Architecture Appeared, and is it Psycholinguistically Plausible
AT NL

1994

I survey some recent applications-oriented NL generation systems, and claim that despite very different theoretical backgrounds, these systems have a remarkably similar architecture in terms of the modules they divide the generation process into, the computations these modules perform, and the way the modules interact with each other. I also compare this `consensus architecture' among applied NLG systems with psycholinguistic knowledge about how humans speak, and argue that at least some aspects of the consensus architecture seem to be in agreement with what is known about human language production, despite the fact that psycholinguistic plausibility was not in general a goal of the developers of the surveyed systems.

View PDFchevron_right

References (45)

  1. 'practical NLG' (http: //www.itri.brighton.ac.uk/projects/rags); the Scottish and German NLG sites (http: //www.cogsci.ed.ac.uk/~jo/gen/snlg/nlg.html and http://www.ling.uni-potsdam.de/ ~stede/nlg-ger.htm respectively) have a variety of useful pointers to systems, litera- ture, and researchers in their respective countries; and the RST site off ers a wide range of information, both computational and linguistic, concerning all aspects of rhetori- cal structure theory and its application (http://www.sil.org/linguistics/RST). A range of papers are available on-line at http://www.iro.umontreal.ca/~scriptum/Publica- tionsMembres.html, and for pointers on AI in general http://www.norvig.com/ is very useful. Finally, we also maintain an almost complete list of NLG systems with linked bibliographical data and pointers to further web-based information at http: //purl.org/net/nlg-list-to which additions are welcome at any time! R
  2. Adorni, G., and M. Zock (eds.). . Trends in Natural Language Generation: An Artifi cial Intelligence Perspective. New York: Springer Verlag.
  3. Andriessen, J., K. de Smedt. and M. Zock. . 'Discourse planning: empirical research and computer models' . In T. Dijkstra and K. de Smedt (eds), Computational Psycholinguistics: AI and Connectionist Models of Human Language Processing, London: Taylor and Francis.
  4. Bateman, J. . 'Enabling technology for multilingual natural language generation: the KPML development environment' . Journal of Natural Language Engineering, (), -.
  5. --. ' Automated discourse generation' . In A. Kent (ed), Encyclopedia of Library and Infor- mation Science, New York: Marcel Dekker, Inc.
  6. Bock, K. . 'Language production: methods and methodologies' . Psychonomic Bulletin and Review, , -
  7. Cahill, L., C. Doran, R. Evans, C. Mellish, D. Paiva, M. Reape, D. Scott, and N. Tipper. . 'Towards a reference architecture for natural language generation systems: the rags project' . Technical Report: ITRI--, Brighton.
  8. Cawsey, A. . 'Using plausible inference rules in description planning' . Proceedings of the th Conference of the European Chapter of the Association of Computational Linguistics (EACL '). Berlin, Germany.
  9. Cole, R., J. Mariani, H. Uszkoreit, A. Zaenen, and V. Zue (eds.). . Survey of the State of the Art in Human Language Technology. Cambridge: Cambridge University Press. http: //www.cse.ogi.edu
  10. Dalianis, H. . ' Aggregation in natural language generation' . Journal of Computational Intel- ligence, ().
  11. Danlos, L., , 'G-TAG: a lexicalized formalism for text generation inspired from tree adjoining grammar: TAG issues' . In A. Abeillé, and O. Rambow (eds.), Tree-Adjoining Grammars, Stanford, Calif: CSLI.
  12. de Smedt, K., H. Horacek. and M. Zock. . 'Some problems with current architectures in Natural Language Generation' . In: G. Adorni and M. Zock (: -).
  13. Elhadad, M., and J. Robin. . 'SURGE: a comprehensive plug-in syntactic realization com- ponent for text generation' . Technical Report, Computer Science Dept., Ben-Gurion Uni- versity, Beer-Shiva, Israel.
  14. Gal, A., G. Lapalme, P. Saint Dizier, and H. Somers. . PROLOG for Natural Language Processing. Chichester: J. Wiley and Sons.
  15. Halliday, M. A. K. . An Introduction to Functional Grammar, London: Arnold.
  16. Harbusch, K., W. Finkler, and A. Schauder. . 'Incremental syntax generation with tree adjoining grammars' . W. Brauer and D. Hernandez (eds.), Verteilte Kuenstliche Intelligenz und kooperatives Arbeiten, Berlin: Springer, -.
  17. Hovy, E. . 'Planning coherent multisentential text' . Buff alo: ACL.
  18. --. ' Automated discourse generation using discourse structure relations' . Artifi cial Intel- ligence, , -.
  19. --. 'Language generation' . In Cole et al. (: -).
  20. Iordanskaija, L., R. Kittredge, and A. Polguère. . 'Lexical selection and paraphrase in a meaning-text generation model' . In Paris (: -).
  21. Kölln, M. . 'Textproduktion als intentionaler, benutzerorientierter Prozess' . St. Augustin: Infi x: DISKI, .
  22. Levelt, W. . Speaking: From Intention to Articulation. Cambridge, Mass.: MIT Press.
  23. McDonald, D. . 'Natural language generation' . In R. Dale, H. Moisl, and H. Somers (eds.), A Handbook of Natural Language Processing Techniques. New York: M. Dekker Inc.
  24. McKeown, K. . 'Discourse strategies for generating natural-language text' . Artifi cial Intel- ligence, , -
  25. Mann, W., and C. Matthiessen. . 'Demonstration of the Nigel Text Generation Computer Program' . In J. Benson and W. Greaves (eds.), Systemic Functional Approaches to Discourse, Norwood, NJ: Ablex Publ. Company.
  26. --and S. A. Th ompson. . 'Rhetorical structure theory: description and construction of text structures' . In G. Kempen (ed.), Natural Language Generation: Recent Advances in Artifi cial Intelligence, Psychology, and Linguistics. Dordrecht: Kluwer Academic Publishers, -.
  27. Maybury, M. . Planning multisentential English text using communicative acts, Ph.D. thesis, University of Cambridge.
  28. Mel'čuk, I. . Dependency Syntax: Th eory and Practice. New York: State University of New York Press.
  29. Meteer, M. . Expressibility and the Problem of Effi cient Text Planning, London: Pinter.
  30. Moore, J. D., and C. L. Paris. . 'Constructing coherent texts using rhetorical relations' . Pro- ceedings of the th Annual Conference of the Cognitive Science Society.
  31. ----. 'Planning text for advisory dialogues: capturing intentional and rhetorical information' . Computational Linguistics, ().
  32. Nogier, J. F., and M. Zock. . 'Lexical choice by pattern matching' . Knowledge Based Systems, (): -.
  33. Nicolov, N. . ' Approximate text generation from non-hierarchical representation in a declarative framework' . Ph.D. thesis, University of Edinburgh.
  34. Paiva, D. . ' A survey of applied natural language generation systems' . Technical Report ITRI--, Brighton. http://www.itri.brighton.ac.uk/techreports.
  35. Paris, C. L. . User Modelling in Text Generation. London: Frances Pinter.
  36. --W. Swartout, and W. Mann (eds.). . Natural Language Generation in Artifi cial Intel- ligence and Computational Linguistics. Boston: Kluwer Academic Publishers.
  37. Reiter, E., and R. Dale . Building Natural Language Generation Systems. Cambridge: Cam- bridge University Press.
  38. Sacerdoti, E. . A Structure for Plans and Behavior. Amsterdam: North Holland.
  39. Stede, M. . Lexical Semantics and Knowledge Representation in Multilingual Text Genera- tion. Dordrecht: Kluwer.
  40. Stone, M., and C. Doran. . 'Sentence planning as description using tree adjoining gram- mar' . Proceedings of the th Annual Meeting of the Association for Computational Linguistics and the th Conference of the European Chapter of the Association for Computational Lin- guistics (ACL-EACL '), -. Madrid: Spain.
  41. Teich, E. . Systemic Functional Grammar in Natural Language Generation: Linguistic Description and Computational Representation. London: Cassell Academic Publishers.
  42. Vander Linden, K. . 'Natural language generation' . D. Jurafsky and J. Martin (eds.), Speech and Language Processing: An Introduction to Speech Recognition, Computational Linguistics and Natural Language Processing. New Jersey: Prentice-Hall.
  43. Wanner, M. . 'Lexical choice in text generation and machine translation' . Machine Transla- tion. (-), -.
  44. Zock, M. . 'Th e power of words in message planning' . Proceedings of the th International Conference on Computational Linguistics. Copenhagen.
  45. --and G. Adorni. . 'Introduction' to Adorni and Zock ().

Related papers

Natural language production as a process of decision-making under constraints
David McDonald

1980

A theory of the llnguistic conponent of the language production process has been developed, and has been used as the basis of a computer program ("MUNIBLE") that produces texts for five experimental "micro-speakers". The theory is based on a view of production as a goal-directed, decision-making process. The speakers goals ("messages") are interpreted as a program of decisions to be made, ordered according to their relative importance and dependencies. An explicit representation of the results of earlier decisions is used to constrain later ones. Goals may be described to the linguistic component using any representation the designer chooses provided they can be enumerated as a hierarchy of relations in a fixed vocabulary. A dictionary and set of interface ftnctions must be written to interpret the vocabulary for the linguistic component. Pending decisions and the results of earlier decisions are represented as a surface-level, syntactic constituent siructure. Texts are produced by realizing each goal-relation in turn according to the decisionprocedure given by its dictionary entry. Decisions specify a sequence of linguistic actions that may be described as the instantiation and traversal of a phrasal schema selected from the grammar. The relation's arguments are mapped into the leaves of the phrase which is then traversed interpreted top-down and left-to-right by a uniform, data-directed controller that produces the text by executing the actions specified by the phrase. All decisions are local to the linguistic context at the position of the controller. Decisions must be indelible, i.e. not retractable-the controller does not backup. Because of these properties, the process is subject to structurally-induced linguistic constrains that govern when a decision can be made, the kinds of information it may appeal to, and what it may effect. Given certain assumptions about how the speaker structures its input goals, the process can be guarenteed to run at a bounded rate and in linear time with the size of the input. The use of an explicit linguistic structure as the representation of given and planned decisions, makes it possible to write general purpose rules and heuristics that apply directly in terms of the representational structure and need know nothing about its semantic content. An elaborate grammar has been written including rules for word order and morphology, agreement, subordination, thematic transformations, ellipsis, wh-movement, and subsequent reference.

View PDFchevron_right
Building natural language generation systems
Robert Dale

Natural Language Engineering, 1997

The book is about natural language generation (NLG), which is a sub®eld of arti®cial intelligence and computational linguistics that is concerned with building computer software systems that can produce meaningful texts in English or other human languages from some underlying non-linguistic representation of information. In the introduction, the ®eld of NLG is brie¯y characterized from research-and applicationoriented perspectives and illustrated by screen shots produced by several systems. Then, conditions for bene®cial uses of this technology are elaborated and contrasted with conditions where other techniques are more appropriate. Moreover, methods for determining the intended functionality of a system to be built are discussed. The main sections of the book are devoted to the prototypical architecture of application-oriented NLG systems and their major processing phases: document planning, microplanning and surface realization. Each of these three phases is illustrated by a number of detailed examples, demonstrating the successive re®nements of utterance speci®cations in the course of processing. In the ®nal section, embedding of the natural language processing technology is discussed featuring typography, combined uses with graphics and hypertext, as well as integration with speech. The methods are illustrated by a large number of examples Ð the book contains more than 120 ®gures on its 248 pages. At the end of each section, a number of useful references for further reading are related to the section topics. In the appendix, a table summarizing the 35 systems referred in the book is given.

View PDFchevron_right
Natural Language Generation: Scope, Applications and Approaches
Manu Madhavan

Natural Language Generation is a subfield of com- putational linguistic that is concerned with the computer systems which can produce understandable texts in some human lan- guages. The system uses machine understandable logical form as input and produces syntactically and semantically valid sentences in natural language. The different stages of NLG include Content selection, Lexical selection, Sentence structuring and Discourse planning. The applications of NLG include text summarization, machine translation and question answering. The effectiveness of the NLG depends on the efficiency of internal knowledge representation. An ontology based Knowledge representation will improve the output text quality. This work also discusses the scope of applying Karaka relations in language modeling for NLG.

View PDFchevron_right
Natural Language Generation in Artificial Intelligence and Computational Linguistics
Cecile Paris

The Kluwer International Series in Engineering and Computer Science, 1991

A number of collections of papers from the field of natural language generation (NLG) have been published over the last few years: Kempen (1987), Zock and Sabah (1988), Dale, Mellish, and Zock (1990), and now the present volume. All have in common that they are derived in one way or another from workshops on the subject, and should therefore make available new and often exploratory research in a timely fashion. If such a book is to be more than a conference proceedings, it has to do a little more too, of course; it should present the research in more detail than a conference proceedings would, there should be greater cohesion amongst the papers, and it should be produced to an appropriate standard. The present book, like its predecessors, succeeds on some counts but fails on others. The papers in the book are organized into three strands, described in turn below: text planning, lexical choice, and grammatical resources. The balance between these is rather skewed, however: the first section contains eight papers, and the second and third contain only three papers each.

View PDFchevron_right
Jornadas de Seguimiento de Proyectos, 2009 Programa Nacional de Tecnoloǵıas Informáticas Development and Validation of an Architecture for Natural Language Generation (DIVAGALAN)
Gabriel Amores

2014

At the start of the project, research in the field of dialogue systems had not addressed issues of natural language generation that are an integral part of the communication cycle. Natural language generation (NLG) research had achieved practical solutions to specific tasks as independent research modules, but they were difficult to interrelate and integrate with other applications. The first goal of the project was the development of a flexible and modular software solution, capable of working with ontologies and the emotional content of messages. This solution should provide a set of reusable software components capable of generating texts suitable for different tasks in different domains. The second goal of the project was to study the application of NLG in spoken dialogue systems in a domotic environment.

View PDFchevron_right
580 California St., Suite 400
San Francisco, CA, 94104
© 2025 Academia. All rights reserved