Update README.md

README.md

@@ -26,29 +26,25 @@ lr_schedule = LinearWarmup
 embeds_dropout_prob = 0.1
 ```
 ## Performance
-We use the GermanDPR test dataset as ground truth labels and run two experiments to compare how a BM25 retriever performs with or without reranking with our model. The first experiment runs retrieval on the full German Wikipedia (>2million passages) and second experiment runs retrieval on the GermanDPR dataset only (<5000 passages). Both experiments use 1025 queries. Note that the second experiment is evaluating on a much simpler task because of the smaller dataset size, which explains strong BM25 retrieval performance.
+We use the GermanDPR test dataset as ground truth labels and run two experiments to compare how a BM25 retriever performs with or without reranking with our model. The first experiment runs retrieval on the full German Wikipedia (more than 2 million passages) and second experiment runs retrieval on the GermanDPR dataset only (not more than 5000 passages). Both experiments use 1025 queries. Note that the second experiment is evaluating on a much simpler task because of the smaller dataset size, which explains strong BM25 retrieval performance.
 
-Full German Wikipedia:
+### Full German Wikipedia (more than 2 million passages):
 BM25 Retriever without Reranking
------------------
-recall@3: 0.4088 (419 / 1025)
-mean_reciprocal_rank@3: 0.3322
+- recall@3: 0.4088 (419 / 1025)
+- mean_reciprocal_rank@3: 0.3322
 
 BM25 Retriever with Reranking Top 10 Documents
------------------
-recall@3: 0.5200 (533 / 1025)
-mean_reciprocal_rank@3: 0.4800
+- recall@3: 0.5200 (533 / 1025)
+- mean_reciprocal_rank@3: 0.4800
 
-Germandpr only:
+### GermanDPR Dataset only (not more than 5000 passages):
 BM25 Retriever without Reranking
------------------
-recall@3: 0.9102 (933 / 1025)
-mean_reciprocal_rank@3: 0.8528
+- recall@3: 0.9102 (933 / 1025)
+- mean_reciprocal_rank@3: 0.8528
 
 BM25 Retriever with Reranking Top 10 Documents
------------------
-recall@3: 0.9298 (953 / 1025)
-mean_reciprocal_rank@3: 0.8813
+- recall@3: 0.9298 (953 / 1025)
+- mean_reciprocal_rank@3: 0.8813