Mirror/MarginaliaSearch
1
0
Fork 0
mirror of https://github.com/MarginaliaSearch/MarginaliaSearch.git synced 2025-02-23 21:18:58 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

(index) Reduce the value of site and site-adjacent in BM25P calculations

Browse Source
This commit is contained in:
Viktor Lofgren 2024-01-03 15:20:18 +01:00
parent f732f6ae6f
commit 1f3b89cf28
1 changed files with 13 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
code/features-index/result-ranking/src/main/java/nu/marginalia/ranking/factors/Bm25Factor.java
View File

@ -53,9 +53,11 @@ public class Bm25Factor {
} }
private static double evaluatePriorityScore(SearchResultKeywordScore keyword) { private static double evaluatePriorityScore(SearchResultKeywordScore keyword) {
int pcount = keyword.positionCount();
double qcount = 0.; double qcount = 0.;
if ((keyword.encodedWordMetadata() & WordFlags.Site.asBit()) != 0) if ((keyword.encodedWordMetadata() & WordFlags.Site.asBit()) != 0)
qcount += 2.; qcount += 0.5;
if ((keyword.encodedWordMetadata() & WordFlags.SiteAdjacent.asBit()) != 0) if ((keyword.encodedWordMetadata() & WordFlags.SiteAdjacent.asBit()) != 0)
qcount += 0.5; qcount += 0.5;
if ((keyword.encodedWordMetadata() & WordFlags.UrlPath.asBit()) != 0) if ((keyword.encodedWordMetadata() & WordFlags.UrlPath.asBit()) != 0)
@ -66,12 +68,16 @@ public class Bm25Factor {
qcount += 2.5; qcount += 2.5;
if ((keyword.encodedWordMetadata() & WordFlags.Title.asBit()) != 0) if ((keyword.encodedWordMetadata() & WordFlags.Title.asBit()) != 0)
qcount += 1.5; qcount += 1.5;
if ((keyword.encodedWordMetadata() & WordFlags.Subjects.asBit()) != 0)
qcount += 1.25; if (pcount > 2) {
if ((keyword.encodedWordMetadata() & WordFlags.NamesWords.asBit()) != 0) if ((keyword.encodedWordMetadata() & WordFlags.Subjects.asBit()) != 0)
qcount += 0.25; qcount += 1.25;
if ((keyword.encodedWordMetadata() & WordFlags.TfIdfHigh.asBit()) != 0) if ((keyword.encodedWordMetadata() & WordFlags.NamesWords.asBit()) != 0)
qcount += 0.5; qcount += 0.25;
if ((keyword.encodedWordMetadata() & WordFlags.TfIdfHigh.asBit()) != 0)
qcount += 0.5;
}
return qcount; return qcount;
} }