- Citation-Key:
- Fuhr/Roelleke:94
- Title:
- A Probabilistic Relational Algebra for the Integration of Information Retrieval and Database Systems
- Author(s):
- N. Fuhr
- T. Rölleke
- Journal:
- ACM Transactions on Information Systems
- Volume:
- 14
- Number:
- 1
- Page(s):
- 32--66
- Year:
- 1997
- Abstract:
- We present a probabilistic data model which is based on relations in non-first-normal-form (NF2). Here, tuples are assigned probabilistic weights giving the probability that a tuple belongs to a relation. This way, imprecise attribute values are modelled as a probabilistic subrelation. For information retrieval, the set of weighted index terms of a document can be represented in the same way, thus supporting the integration of information retrieval and database systems. By redefining the relational operators for this type of relations, the result of each operator is again a probabilistic NF2 relation, where the weight of a tuple gives the probability that this tuple belongs to the result.
- Classification(s):
- I.2.3, H.2.1
- Subject descriptor(s):
- data models, probabilistic reasoning
- Keywords:
- DBMIRS, vague queries
Fulltext as PS