Natural Language Generation: Scope, Applications and Approaches

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.

1997

In this article, we g i v e a n o verview 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 used to build simple but practical working systems now. We also provide pointers to techniques in the literature that are appropriate for more complicated scenarios.

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.

Language, 1992

2003

Topic 1 NLG Overview Course Objectives • to give a broad overview of the field of nlg • to show the state of the art in nlg • to give an overview of the more prominent nlg systems and approaches • to highlight the current major issues in nlg research

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.

1975

A program framework has been designed in which the linguistic 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 ...

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.

Computational Linguistics, 1998

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.