carlesoctav commited on
Commit
cae641c
1 Parent(s): 6be3c64

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -3
README.md CHANGED
@@ -8,6 +8,14 @@ tags:
8
 
9
  ---
10
 
 
 
 
 
 
 
 
 
11
  # carles-undergrad-thesis/indobert-mmarco-hardnegs-bm25
12
 
13
  This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
@@ -72,9 +80,11 @@ print(sentence_embeddings)
72
 
73
  ## Evaluation Results
74
 
75
- <!--- Describe how your model was evaluated -->
76
-
77
- For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=carles-undergrad-thesis/indobert-mmarco-hardnegs-bm25)
 
 
78
 
79
 
80
  ## Training
 
8
 
9
  ---
10
 
11
+ This model utilizes a newer version of Sentence Transformers. If you're having trouble using this model, please try installing the latest version of Sentence Transformers with:
12
+
13
+ ```bash
14
+ pip install --upgrade --force-reinstall --no-deps git+https://github.com/UKPLab/sentence-transformers.git
15
+ ```
16
+
17
+
18
+
19
  # carles-undergrad-thesis/indobert-mmarco-hardnegs-bm25
20
 
21
  This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
 
80
 
81
  ## Evaluation Results
82
 
83
+ | Model | Mmarco Dev | | MrTyDi Test | | Miracal Test | |
84
+ |-----------------------------------------|------------|----------------|-------------|----------------|--------------|----------------------------|
85
+ | | MRR@10 | R@1000 | MRR@10 | R@1000 | NCDG@10 | R@1K |
86
+ | $\text{BM25 (Elastic Search)}$ | .114 | .642 | .279 | .858 | .391 | .971 |
87
+ | $\text{IndoBERT}_{\text{DOTHardnegs}}$ | .232 | .847 | .471 | .921 | .397 | .898 |
88
 
89
 
90
  ## Training