Factors Contributing to Efficiency in Natural Language Generation

McDonald, David D.; Vaughan, Marie M.; Pustejovsky, James

doi:10.1007/978-94-009-3645-4_12

Cited by 27 publications

(10 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Heidegger's philosophical writings are the only example that comes to mind; these are notoriously unreadable. (Many generators, most obviously input-driven generators (McDonald et al 1987), straightforwardly express their input, and run into no problems of goal conflicts. This only works, however, because their inputs are fairly close, in various ways, to the target language sentences they are expected to lead to.…”

Section: Multiple Interacting Goalsmentioning

confidence: 99%

“…For example, traversal of a downward link might cause a subroutine call, and arriving at a node for a verb-concept might lead to unifying slots with cases. In general it is common for the structure of the input to directly determine the sequence and constituency of the text, as McDonald has observed (McDonald et al 1987). Deep-structure-like inputs have the advantage that they can somewhat more plausibly be considered to be 'meaning'.…”

Section: Linguistic Heritagementioning

confidence: 99%

“…Unlike previous studies of generation as a computational problem (McDonald 1983(McDonald , 1987b(McDonald , 1988McDonald et al 1987) this paper does not assume any particular computational mechanism; in particular, it does not assume that a generator necessarily makes choices, builds intermediate representations, or is composed of modules.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Some Neglected Aspects of the Generation Task

Ward

1992

Computational Intelligence

View full text Add to dashboard Cite

Looking to the future, generators will have more knowledge of language and will have to deal with inputs which are very rich in information. As a result, several problems will become more acute, including selecting what to say at the sub-proposition level and dealing with interaction among goals and dependencies among choices. This paper explains how these problems arise and why they are hard to handle within traditional architectures for generation. It also discusses why these issues have not been well addressed; reasons include the current lack of demanding applications, undue respect for linguistic traditions, the use of reverse engineering to determine generator inputs, and the tendency to research only one issue at a time.

show abstract

Section: Multiple Interacting Goalsmentioning

confidence: 99%

Section: Linguistic Heritagementioning

confidence: 99%

See 1 more Smart Citation

Some Neglected Aspects of the Generation Task

Ward

1992

Computational Intelligence

View full text Add to dashboard Cite

show abstract

“…Since we have positioned the level of the specification language so as to fit the decomposition reflected in our own work and to expedite the use of Mumble-86 by other researchers, the answer can be given quite precisely. For a more complete discussion of our approach and how it contrasts with other work, see (McDonald, Meteer, & Pustejovsky, 1987). Overall we can divide the generation process into three coarse stages:…”

Section: Mumble's Place In the Generation Processmentioning

confidence: 99%

From Water to Wine: Generating Natural Language Text from Today's Applications Programs

McDonald¹,

Meteer²

1988

Self Cite

View full text Add to dashboard Cite

In this paper we present a means of compensating for the semantic deficits of linguistically naive underlying application programs without compromising principled grammatical treatments in natural language generation. We present a method for building an interface from today's underlying application programs to the linguistic realization component Mumble-86. The goal of the paper is not to discuss how Mumble works, but to describe how one exploits its capabilities. We provide examples from current generation projects using Mumble as their linguistic component.

show abstract

“…(The efficiency of this type of architecture is discussed at length in McDonald, Meteer, and Pustejovsky, 1987.) The components and levels of representation in SPOKESMAN are shown in Figure 2.…”

Section: 1 Components Of Spokesmanmentioning

confidence: 99%

SPOKESMAN: data-driven, object-oriented natural language generation

Meteer¹

[1991] Proceedings. The Seventh IEEE Conference on Artificial Intelligence Application

View full text Add to dashboard Cite

This paper describes the SPOKESMAN natural language generation system, which is a domain independent component designed to produce text for an application program. Our approach to natural language generation uses the structures from the application program it is working for to directly drive the generation of descriptions and explanations. SPOKESMAN is datadriven in that it uses application program structures to guide its organization of the text, and object-oriented in that it uses links into the application's hierarchical domain model to determine how to express the objects that populate those structures. This approach is more efficient, since the content to be expressed is provided by the application program, rather than having to be constructed by the generator, and since the object types constrain the possible ways the content can be expressed. Careful design of intermediate levels of representation internal to the generator ensure that the utterance being composed will be both expressible and grammatical. Examples are taken from BBN's Semi-Automated Forces simulation. Topic: Natural language generation, explanation Domain area: Simulations/ Military Language/tool: Common Lisp, Flavors/CLOS Status: incorporated into final demonstration systems Effort: 3 yrs Impact: Spokesman provides application programs with the ability to communicate with their users: describing their underlying structures, explaining their actions, and justifying their decisions.

show abstract

Factors Contributing to Efficiency in Natural Language Generation

Cited by 27 publications

References 9 publications

Some Neglected Aspects of the Generation Task

Some Neglected Aspects of the Generation Task

From Water to Wine: Generating Natural Language Text from Today's Applications Programs

SPOKESMAN: data-driven, object-oriented natural language generation

Contact Info

Product

Resources

About