1997
DOI: 10.1007/3-540-63233-6_496
|View full text |Cite
|
Sign up to set email alerts
|

The case for graph-structured representations

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
9
0

Year Published

1999
1999
2009
2009

Publication Types

Select...
5
2

Relationship

0
7

Authors

Journals

citations
Cited by 26 publications
(9 citation statements)
references
References 11 publications
0
9
0
Order By: Relevance
“…Practical experience in the development of CBR systems has demonstrated that a simple feature vector is not adequate to represent the complexity of cases encountered in practice: it is often the case that cases have internal structure that needs to be represented [8,1,9,10,11]. Given that research on structural case representations is driven by the requirements of practical applications there is considerable variety in the types of structured representation that has been covered in the literature.…”
Section: Structured Representationsmentioning
confidence: 99%
See 1 more Smart Citation
“…Practical experience in the development of CBR systems has demonstrated that a simple feature vector is not adequate to represent the complexity of cases encountered in practice: it is often the case that cases have internal structure that needs to be represented [8,1,9,10,11]. Given that research on structural case representations is driven by the requirements of practical applications there is considerable variety in the types of structured representation that has been covered in the literature.…”
Section: Structured Representationsmentioning
confidence: 99%
“…• The next most general structure is a network structure (typically a semantic network): there is a long history of semantic network-based case representations in CBR and in the related research area of analogical reasoning [2,14,11]. Whereas in a hierarchical representation there is only one link type, the part-of link, in a network structure there can be many link types with a rich link semantics.…”
Section: Structured Representationsmentioning
confidence: 99%
“…In most approaches, cases are represented by trees [23], graphs [24,25] and semantic nets [24]. Many applications deal with the layout/design [26,27] or planning problems [24,25].…”
Section: Structured Cases In Cbrmentioning
confidence: 99%
“…A similar approach [21] uses a CBR+EBL similarity metric that is able to assign a relevance measure to each matching fact. Up to now, practically all the existing similarity measures assume that cases are represented just by collections of feature-value pairs, however we have started to see the need for more structured representations in complex domains [10], [107] and therefore for new approaches to similarity such as graph similarity measures already used in pattern recognition [31], [93], or using domain knowledge to describe declarative biases to guide the retrieval process [10]. In [88] a formal framework for the construction of similarity metrics which subsume boolean, numeric and structured measures of similarity is introduced.…”
Section: Indexing/retrieval/selectionmentioning
confidence: 99%