|
1. |
AUTOMATIC GENERATION OF TECHNICAL DOCUMENTATION |
|
Applied Artificial Intelligence,
Volume 9,
Issue 3,
1995,
Page 259-287
EHUD REITER,
CHRIS MELLISH,
JOHN LEVINE,
Preview
|
PDF (1004KB)
|
|
摘要:
Natural-language generation (NLG) techniques can be used to automatically produce technical documentation from a domain knowledge base and linguistic and contextual models. We discuss this application of NLG technology from both a technical and a usefulness (costs and benefits) perspective. This discussion is based largely on our experiences with the Intelligent Documentation Advisory System (IDAS) documentation-generation project, and the reactions that various interested people from industry have had to IDAS. We hope that this summary of our experiences with IDAS and the lessons we have learned from it will be beneficial for other researchers who wish to build technical documentation-generation systems.
ISSN:0883-9514
DOI:10.1080/08839519508945476
出版商:Taylor & Francis Group
年代:1995
数据来源: Taylor
|
2. |
STATLOG: COMPARISON OF CLASSIFICATION ALGORITHMS ON LARGE REAL-WORLD PROBLEMS |
|
Applied Artificial Intelligence,
Volume 9,
Issue 3,
1995,
Page 289-333
R. D. KING,
C. FENG,
A. SUTHERLAND,
Preview
|
PDF (1532KB)
|
|
摘要:
This paper describes work in the StatLog project comparing classification algorithms on large real-world problems. The algorithms compared were from symbolic learning (CART. C4.5, NewID, AC2,ITrule, Cal5, CN2), statistics (Naive Bayes, k-nearest neighbor, kernel density, linear discriminant, quadratic discriminant, logistic regression, projection pursuit, Bayesian networks), and neural networks (backpropagation, radial basis functions). Twelve datasets were used: five from image analysis, three from medicine, and two each from engineering and finance. We found that which algorithm performed best depended critically on the data set investigated. We therefore developed a set of data set descriptors to help decide which algorithms are suited to particular data sets. For example, data sets with extreme distributions (skew > l and kurtosis > 7) and with many binary/categorical attributes (>38%) tend to favor symbolic learning algorithms. We suggest how classification algorithms can be extended in a number of directions.
ISSN:0883-9514
DOI:10.1080/08839519508945477
出版商:Taylor & Francis Group
年代:1995
数据来源: Taylor
|
3. |
HYBRID MODELS OF UNCERTAINTY IN PROTEIN TOPOLOGY PREDICTION |
|
Applied Artificial Intelligence,
Volume 9,
Issue 3,
1995,
Page 335-351
SIMON PARSONS,
Preview
|
PDF (681KB)
|
|
摘要:
Predicting protein structure is an important problem in molecular biology, and one that has attracted much attention. It is also a difficult problem, since the available data are incomplete and pervaded with uncertainty. This paper describes models for the prediction of an intermediate level of protein structure known as the topology of the protein. The models handle uncertainty explicitly, making use of probability, possibility, and evidence theories singly and in combination to handle different aspects of the problem.
ISSN:0883-9514
DOI:10.1080/08839519508945478
出版商:Taylor & Francis Group
年代:1995
数据来源: Taylor
|
4. |
BOOKS RECEIVED |
|
Applied Artificial Intelligence,
Volume 9,
Issue 3,
1995,
Page 353-354
Preview
|
PDF (42KB)
|
|
ISSN:0883-9514
DOI:10.1080/08839519508945479
出版商:Taylor & Francis Group
年代:1995
数据来源: Taylor
|
|