Jimmy Lin
Jimmy Lin
Tactical: + What's the next experiment I should run? + Is _A_ or _B_ more promising? + When should I arXiv this? Strategic: + What do I want to be...
Hi @joaopalotti - Looking at your code, `TrecEval` takes a `TrecRun`, which reads an external file into a DF. So if we generate a DF that corresponds to the same...
I'm happy to provide all the runs in Anserini for your unit tests!
evaluate_anserini_bm25.py retrieves 1000 documents for each query no matter which k I set in payload
@thakur-nandan File an issue to redirect the BM25 baselines over to Pyserini? Will save you from having to answer such queries again in the future...
Hi @sudokim thanks for the PR! Do you have any idea if effectiveness improves as a result of switching the analyzer? E.g., on MIRACL or Mr.Tydi?
Great! Do you happen to have MRR scores? And also results on MIRACL? (Which will give us nDCG scores.)
Awesome, that's great! We'll get this merged in... but it triggers a long dependency chain... we need to fix the regression... we also need to fix the pre-built indexes for...
@tteofili tells me this is the fix: https://github.com/apache/lucene/pull/13090
Interesting, @tteofili - I'm playing with JDK 21. (On master, we are still on JDK 11.) Note, this is still on Lucene 9.9.1: with `-Xmx 31G`, got `java.lang.OutOfMemoryError: Java heap...
Closed by #2448