Update README.md

Files changed (1) hide show

README.md CHANGED Viewed

@@ -23,7 +23,7 @@ SOTA 🌟, zero-shot model (Macaw 🦜 ).
 Remarkably, using DREAM’s 💭 scene elaborations 🖼️ as additional context improves📈 the answer accuracy across different downstream QA systems 🤖 and on different end-tasks 📝 (including beyond that obtainable by further fine-tuning the QA system on DREAM’s training data 📚). Our approach is question-agnostic 💫, leaves end-task QA models unchanged ✨, and thus easily portable to other QA models 🌟, suggesting exciting opportunities for further improving and exploiting scene elaborations to better solve new problems. 💡
-We invite you to try out 💭DREAM 💭 for your own application!


23
24	Remarkably, using DREAM’s 💭 scene elaborations 🖼️ as additional context improves📈 the answer accuracy across different downstream QA systems 🤖 and on different end-tasks 📝 (including beyond that obtainable by further fine-tuning the QA system on DREAM’s training data 📚). Our approach is question-agnostic 💫, leaves end-task QA models unchanged ✨, and thus easily portable to other QA models 🌟, suggesting exciting opportunities for further improving and exploiting scene elaborations to better solve new problems. 💡
25
26	+ We invite you to try out DREAM 💭 for your own application!
27
28
29