Harman, D, 1989, How e ective is suxing. Journal of the American Society for Information Science 42(1), 7--15.  @ NUS  Home/Search   Document Not in Database   Summary   Related Articles   Check

....very similar to the original linear interpolation of global and local probabilities of equation 1. The added frequencies can be used to replace df(k) and tf (k, d) in the weighting formula of figure 2. 1 # i ) tf (t, d) A similar algorithm was introduced earlier by Harman [7] for on line stemming. Harman did not present her algorithm as an extension of Boolean searching, but instead called it grouping . If collection frequencies instead of document frequencies are used, then this method has the nice characteristic that on line morphological generation treating the ....

D. Harman. How e#ective is su#xing? Journal of the American Society for Information Science, 42(1):7--15, 1991.

....presented in this paper were developed in co operation with Wessel Kraaij from TNO TPD Delft as a preparation for the ocial TREC experiments. He deserves the credits for the idea to add the manually disambiguated run to our experiments and for pointing out the reference to Harman s grouping method [4]. We are most grateful to Wessel for his advice and assistance. Furthermore, we like to thank Lynn Packwood for the manual disambiguation of the Van Dale dictionary output and Thijs Westerveld for implementing the interface on the corpus dictionary. Appendix: probabilistic weighting algorithms ....

....respectively the document frequencies and the term frequencies of the disjuncts can be added beforehand. The added frequencies can be used to replace df(k) and tf (k; d) in the weighting formula of table 5. The resulting ranking algorithm for Boolean queries was introduced earlier by Harman [4] for on line stemming. Harman did not present her algorithm as an extension of Boolean searching, but instead called it grouping . A somewhat similar approach for cross language information retrieval was adopted by Ballesteros and Croft [1] by using a synonym operator on term translations with ....

D. Harman. How eective is suxing? Journal of the American Society for Information Science, 42(1):7-15, 1991.

.... recall without losing too much precision, however, a comparison of the Lovins stemmer, the S stemmer, and the Porter stemmer with a baseline of no stemming at all, concluded after detailed evaluation that none of the three stemming algorithms consistently improves retrieval for English documents [4]. It was argued that the evaluation measures were not appropriate, and new measures were proposed for evaluating the performance of di erent stemming algorithms [5] After experimentation, it was concluded that stemming is almost always bene cial for English, except for long queries at low recall ....

Donna Harman. How Eective is Suxing? Journal of the American Society for Information Science, 42(1):7-15, 1991.

....Instead, the document frequencies and the term frequencies of the disjuncts respectively, can be added beforehand. The added frequencies can be used to replace df(k) and tf (k; d) in the weighting formula of table 2. A similar ranking algorithm for Boolean queries was introduced earlier by Harman [7] for on line stemming. Harman did not present her algorithm as an extension of Boolean searching, but instead called it grouping . Instead of adding the document frequencies, the TNO vector engine calculates the actual document frequencies of the disjuncts, by merging their postings at run time. ....

D. Harman. How eective is suxing? Journal of the American Society for Information Science, 42(1):7-15, 1991.

....The added frequencies can be used to replace df(k) and tf (k; d) in the weighting formula of gure 2. P (T i =t i1 [ T i =t i2 [ T i =tim jD=d) 1 i ) P m j=1 df(t ij ) P t df(t) i P m j=1 tf (t ij ; d) P t tf (t; d) A similar algorithm was introduced earlier by Harman [7] for on line stemming. Harman did not present her algorithm as an extension of Boolean searching, but instead called it grouping . If collection frequencies instead of document frequencies are used, then this method has the nice characteristic that on line morphological generation treating the ....

D. Harman. How eective is suxing? Journal of the American Society for Information Science, 42(1):7-15, 1991.

No context found.

Harman, D, 1989, How e
ective is suxing. Journal of the American Society for Information Science 42(1), 7--15.

No context found.

D. Harman. How e#ective is su#xing? Journal of The American Society for Information Science, 42:7--15, 1991.

No context found.

Donna Harman. How eective is suxing? Journal of the American Society for Information Science, 42(1): pages 7-15, 1991.

No context found.

Harman, D.: How e#ective is su#xing? Journal of the American Society for Information Science 42 (1991) 7--15

No context found.

D. Harman. How e#ective is su#xing? Journal of the American Society for Information Science, 42(1):7--15, 1991.

No context found.

D. Harman, 1991. How Eective Is Suxing, Journal of the American Society for Information Science, 42(1):7-15.

Online articles have much greater impact   More about CiteSeer.IST at NUS   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST at NUS - Copyright Penn State and NEC. Hosted by the School of Computing, National University of Singapore.