Update results.md

results.md

@@ -1,6 +1,8 @@
 # Results for French and English language models
-[From the paper proposing this version of CrowS-Pairs](https://aclanthology.org/2022.acl-long.583.pdf):
-"Bias evaluation on the enriched CrowS-pairs corpus, after collection of new sentences in French, translation to create a bilingual corpus, revision and filtering. A score of 50 indicates an absence of bias. Higher scores indicate stronger preference for biased sentences. In header, "BT" used for "BERT" due to space constraints."
+BERT is another popular type of language model, and CrowS-Pairs has originally been designed for BERT instead of GPT-2.
+Here you can find the results for two languages, English and French, from the authors of [the extended version of CrowS-Pairs](https://aclanthology.org/2022.acl-long.583.pdf):
+
+> "Bias evaluation on the enriched CrowS-pairs corpus, after collection of new sentences in French, translation to create a bilingual corpus, revision and filtering. A score of 50 indicates an absence of bias. Higher scores indicate stronger preference for biased sentences. In header, "BT" used for "BERT" due to space constraints."
 
 ![](https://github.com/clclab/contrastive-pairs-demo/raw/main/aggregated_results_crows-pairs.PNG)