Let A be a finite, totally ordered alphabet, and let P be the lexicographic ordering on A\*. Let X be a subset of A\*. The language of minimal words of X is the subset of X composed of the lexicographically minimal word of X for each length: The aim of this paper is to prove that if L is a context-
Evaluation in the context of natural language generation
โ Scribed by C Mellish; R Dale
- Publisher
- Elsevier Science
- Year
- 1998
- Tongue
- English
- Weight
- 184 KB
- Volume
- 12
- Category
- Article
- ISSN
- 0885-2308
No coin nor oath required. For personal study only.
โฆ Synopsis
What role should evaluation play in the development of natural language generation (๏ฎ๏ฌ๏ง) techniques and systems? In this paper we describe what is involved in natural language generation, and survey how evaluation has figured in work in this area to date. We comment on the issues raised by this existing work and on how the problems of ๏ฎ๏ฌ๏ง evaluation are different from the problems of evaluating work in natural language understanding. The paper is concluded by suggesting a way forward by looking more closely at the component problems that are addressed in natural language generation research; a particular text generation application is examined and the issues that are raised in assessing its performance on a variety of dimensions are looked at.
๐ SIMILAR VOLUMES
In this paper, seven experiments are described in which the effect of contrast categories on the within-category structure of superordinate and basic level natural language concepts was studied. Intension-based and extensionbased predictors originating from both the target category and a contrast ca
This paper describes Bell Labs' efforts in developing core technologies toward natural language call routing (NLCR) applications. NLCR refers to technology allowing callers of a call center to be automatically routed to their desired destination based on natural spoken responses to an open-ended pro
As with human-human interaction, spoken human-computer dialog will contain situations where there is miscommunication. One natural strategy for reducing the impact of miscommunication is selective verification of the user utterance meanings. This paper reports on both context-independent and context