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

(index-ranking) Adjust the BM25P factors a bit

Browse Source 
Since the bleed-flags set by the anchor tags logics have been changed to Site and SiteAdjacent, give them a bit of more importance when set together with ExternalLink.

UrlDomain and UrlPath are also only more consistently only rewarded once.
This commit is contained in:
Viktor Lofgren 2024-01-30 21:27:29 +01:00
parent acc2b4e10f
commit eb59ac8535
1 changed files with 15 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
code/features-index/result-ranking/src/main/java/nu/marginalia/ranking/factors/Bm25Factor.java
View File

@ -57,24 +57,30 @@ public class Bm25Factor {
double qcount = 0.;
if ((keyword.encodedWordMetadata() & WordFlags.Site.asBit()) != 0)
qcount += 0.5;
if ((keyword.encodedWordMetadata() & WordFlags.SiteAdjacent.asBit()) != 0)
qcount += 0.5;
if ((keyword.encodedWordMetadata() & WordFlags.ExternalLink.asBit()) != 0) {
qcount += 2.5;
if ((keyword.encodedWordMetadata() & WordFlags.UrlDomain.asBit()) != 0)
qcount += 2.5;
else if ((keyword.encodedWordMetadata() & WordFlags.UrlPath.asBit()) != 0)
qcount += 1;
qcount += 1.5;
if ((keyword.encodedWordMetadata() & WordFlags.Site.asBit()) != 0)
qcount += 1.25;
if ((keyword.encodedWordMetadata() & WordFlags.SiteAdjacent.asBit()) != 0)
qcount += 1.25;
}
else {
if ((keyword.encodedWordMetadata() & WordFlags.UrlPath.asBit()) != 0)
qcount += 1;
if ((keyword.encodedWordMetadata() & WordFlags.UrlDomain.asBit()) != 0)
qcount += 1.5;
qcount += 3;
else if ((keyword.encodedWordMetadata() & WordFlags.UrlPath.asBit()) != 0)
qcount += 1;
if ((keyword.encodedWordMetadata() & WordFlags.Site.asBit()) != 0)
qcount += 0.5;
if ((keyword.encodedWordMetadata() & WordFlags.SiteAdjacent.asBit()) != 0)
qcount += 0.5;
}
if ((keyword.encodedWordMetadata() & WordFlags.Title.asBit()) != 0)