Kraaij, W.; Pohlmann, R.: Evaluation of a Dutch stemming algorithm (1995)
0.02
0.015214371 = product of:
0.07607185 = sum of:
0.07607185 = weight(_text_:index in 5798) [ClassicSimilarity], result of:
0.07607185 = score(doc=5798,freq=2.0), product of:
0.2250935 = queryWeight, product of:
4.369764 = idf(docFreq=1520, maxDocs=44218)
0.051511593 = queryNorm
0.33795667 = fieldWeight in 5798, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
4.369764 = idf(docFreq=1520, maxDocs=44218)
0.0546875 = fieldNorm(doc=5798)
0.2 = coord(1/5)
- Abstract
- A stemming algorithm enables the recall of text retrieval systems to be enhanced. Describes the development of a Dutch version of the Porter stemming algorithm. The stemmer was evaluated using a method drawn from Paice. The evaluation method is based on a list of groups of morphologically related words. Ideally, each group must be stemmed to the same root. The result of applying the stemmer to these groups of words is used to calculate the understemming and overstemming index. These parameters and the diversity of stem group categories that could be generated from the CELEX database enabled a careful analysis of the effects of each stemming rule. The test suite is highly suited to qualitative comparison of different versions of stemmers
