Sentence Similarity
Safetensors
Japanese
RAGatouille
bert
ColBERT
bclavie commited on
Commit
6eb9800
1 Parent(s): 791a7e2

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -0
README.md CHANGED
@@ -21,6 +21,10 @@ Under Construction, please come back in a few days!
21
 
22
  # Results
23
 
 
 
 
 
24
  (refer to the technical report for exact evaluation method + code. * indicates the best monolingual/out-of-domain result. **bold** is best overall result. _italic_ indicates the task is in-domain for the model.)
25
 
26
  | | JSQuAD | | | | MIRACL | | | | MrTyDi | | | | Average | | |
 
21
 
22
  # Results
23
 
24
+ See the table below for an overview of results, vs previous Japanese-only models and the current multilingual state-of-the-art (multilingual-e5).
25
+
26
+ Worth noting: JaColBERT is evaluated out-of-domain on all three datasets, whereas JSQuAD is partially (English version) and MIRACL & Mr.TyDi are fully in-domain for e5, likely contributing to their strong performance. In a real-world setting, I'm hopeful this could be bridged with moderate, quick (<2hrs) fine-tuning.
27
+
28
  (refer to the technical report for exact evaluation method + code. * indicates the best monolingual/out-of-domain result. **bold** is best overall result. _italic_ indicates the task is in-domain for the model.)
29
 
30
  | | JSQuAD | | | | MIRACL | | | | MrTyDi | | | | Average | | |