161sh/CatgirlIntelligenceAgency
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

(index) Adjust BM25 parameters

Browse Source
This commit is contained in:
Viktor Lofgren 2024-01-03 16:30:46 +01:00
parent 5c2561d05d
commit 109bec372c
1 changed files with 16 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
code/features-index/result-ranking/src/main/java/nu/marginalia/ranking/factors/Bm25Factor.java
View File

@ -56,16 +56,27 @@ public class Bm25Factor {
int pcount = keyword.positionCount(); 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 += 0.5; 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)
qcount += 1.25; if ((keyword.encodedWordMetadata() & WordFlags.ExternalLink.asBit()) != 0) {
if ((keyword.encodedWordMetadata() & WordFlags.UrlDomain.asBit()) != 0)
qcount += 1.25;
if ((keyword.encodedWordMetadata() & WordFlags.ExternalLink.asBit()) != 0)
qcount += 2.5; qcount += 2.5;
if ((keyword.encodedWordMetadata() & WordFlags.UrlDomain.asBit()) != 0)
qcount += 2.5;
else if ((keyword.encodedWordMetadata() & WordFlags.UrlPath.asBit()) != 0)
qcount += 1;
}
else {
if ((keyword.encodedWordMetadata() & WordFlags.UrlPath.asBit()) != 0)
qcount += 1;
if ((keyword.encodedWordMetadata() & WordFlags.UrlDomain.asBit()) != 0)
qcount += 1.5;
}
if ((keyword.encodedWordMetadata() & WordFlags.Title.asBit()) != 0) if ((keyword.encodedWordMetadata() & WordFlags.Title.asBit()) != 0)
qcount += 1.5; qcount += 1.5;