An Introduction to Natural Language Generation (original) (raw)

Natural Language Generation: Scope, Applications and Approaches

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.

Natural Language Generation in Artificial Intelligence and Computational Linguistics

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.

Proceedings of the Linguistic Resources for Automatic Natural Language Generation - LiRA@NLG

2017

The Linguistic Resources for Automatic Natural Language Generation (LiRA@NLG) workshop of the International Natural Language Generation INLG2017 Conference held at Santiago de Compostela, September 4, 2017, brought together participants involved in developing large-coverage linguistic resources and researchers with an interest in expanding real-world Natural Language Generation (NLG) software. Linguists and developers of NLG software have been working separately for many years: NLG researchers are typically more focused on technical issues specific to text generation-where good performance (e.g. recall and precision) is crucial-whereas linguists tend to focus on problems related to the development of exhaustive and precise resources that are mainly 'neutral' visa -vis any NLP application (e.g. parsing or generating sentences), using various grammatical formalisms such as NooJ, TAG or HPSG. However, recent progress in both fields is reducing many of these differences, with largecoverage linguistic resources being more and more used by robust NLP software. For instance, NLG researchers can now use large dictionaries of multiword units and expressions, and several linguistic experiments have shown the feasibility of using large phrase-structure grammars (a priori used for text parsing) in 'generation' mode to automatically produce paraphrases of sentences that are described by these grammars. The eight papers presented at the LiRA@NLG workshop focused on the following questions:  How do we develop 'neutral' linguistic resources (dictionaries, morphological, phrase-structure and transformational grammars) that can be used both to parse and generate texts automatically?  Is it possible to generate grammatical sentences by using linguistic data alone, i.e. with no statistical methods to remove ambiguities? What are the limitations of rule-based systems, as opposed to stochastic ones? The common themes that these articles explore are: how to build large-coverage dictionaries and morphological grammars that can be used by NLG applications, how to integrate a linguistically-based Generation module into a Machine-Translation system, and how to construct a syntactic grammar that can be used by a transformational engine to perform paraphrase generation. Linguists as well as Computational Linguists who work on Automatic Generation based on linguistic methods will find advanced, up-to-the-minute studies on these topics in this volume:  Max Silberztein's article, "Automatic Generation from FOAF to English: Linguistic Contribution to Web Semantics," presents an automatic system capable of generating a large number of English sentences from Friend Of A Friend (FOAF) statements in the RDF Turtle notation using NooJ's transformational engine both in Parse and Generation modes.

Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation

This paper surveys the current state of the art in Natural Language Generation (nlg), defined as the task of generating text or speech from non-linguistic input. A survey of nlg is timely in view of the changes that the field has undergone over the past decade or so, especially in relation to new (usually data-driven) methods, as well as new applications of nlg technology. This survey therefore aims to (a) give an up-to-date synthesis of research on the core tasks in nlg and the architectures adopted in which such tasks are organised; (b) highlight a number of relatively recent research topics that have arisen partly as a result of growing synergies between nlg and other areas of artificial intelligence; (c) draw attention to the challenges in nlg evaluation, relating them to similar challenges faced in other areas of nlp, with an emphasis on different evaluation methods and the relationships between them.

Towards automatic generation of natural language generation systems

Proceedings of the 19th international conference on Computational linguistics -, 2002

This paper considers several important issues for monolingual and multilingual link detection. The experimental results show that nouns, verbs, adjectives and compound nouns are useful to represent news stories; story expansion is helpful; topic segmentation has a little effect; and a translation model is needed to capture the differences between languages.

Linguistic Resources for Automatic Natural Language Generation1

The will of building a structure in education results from the urgency to meet with electronic instrument to the traditional paper-based. In today's society, the use of technology in the management and processing of information is growing in strategic importance for professional communication and, above all, for the reception of broadcast messages in real time. The educational tools are changing; the dictionary gives way to corpora for direct consultation for online teaching and translation. The idea developed by a group of linguists and computer engineers of Work Tools: specialist ambivalent body language, for communication in real time and for teaching. It has the advantage, unlike the others, to make use of fixed forms, bent and acronyms to play specialized languages. So it is composed of :a database that may be changed from time to time; a text type that allows the user to compose, decompose and reformulate the text using acronyms, fixed phrases, but especially with replacement techniques to manipulate images of the sentences DS-DGS reproduction of synthetic text-German Translation-etc.-scroll in real time on the bar.

Linguistic Resources for Automatic Natural Language Generation

2017

This paper presents a linguistic module capable of generating a set of English sentences that correspond to a Resource Description Framework (RDF) statement; I discuss how a generator can control the linguistic module, as well as the various limitations of a pure linguistic framework.

Natural Language Generation and Semantic Technologies

Cybernetics and Information Technologies, 2014

The paper presents a survey of the domain of Natural Language Generation (NLG) with its models, techniques, applications, and investigates how the semantic technologies are drawn into text generation. The idea and facilities of Semantic Web initiative are discussed in connection with the new opportunities offered to the Natural Language Generation.

Proceedings of the Sixth International Natural Language Generation Conference (INLG 2010)

2010

The INLG 2010 programme consists of presentations of substantial, original, and previously unpublished results on all topics related to natural language generation. This year we received 50 submissions (36 full papers and 14 short papers) from 18 different countries from around the world. As in previous years, each submission was reviewed by at least three members of an international programme committee of leading researchers in the field. Based on these reviews 16 submissions were accepted as full papers and 8 as short papers (4 papers were withdrawn). The accepted papers are of the highest quality and cover all of the major aspects of natural language generation. This year, the conference programme includes two keynote speakers. Susan E. Brennan, Professor of Psychology at Stony Brook University, will speak on "Adapting Generation to Addressees: What Drives Audience Design?" and Richard Power of The Open University will present a talk entitled "Ontologies and Text: Can NLG Bridge the Gap?". This year we are also delighted to host the 2010 Generation Challenges organised by Anja Belz, Albert Gatt and Alexander Koller. This is a part of INLG that has been growing in importance over the last number of conferences and is a great addition to the event. The organising committee would like to offer their thanks to our invited speakers for agreeing to join us, the organisers of INLG 2008 for their enormous help, the SIGGEN board for allowing us host the conference and for their assistance, Priscilla Rasmussen at ACL and Alena Moison at TCD for handling finances, the programme committee for their dedicated work, and, most of all, the authors of all submitted papers. We have also received generous sponsorship from the Centre for Next Generation Localisation and Science Foundation Ireland for which we are extremely grateful. Finally, we would like to welcome you to Trim and hope that you have an enjoyable and inspiring visit. We will leave you with an Irish proverb in the spirit of INLG: Tír gan teanga, tír gan anam.