Update README.md

README.md

@@ -4,8 +4,6 @@ language: ar
 widget:
  - text: "قفا نبك من ذِكرى حبيب ومنزلِ  بسِقطِ اللِّوى بينَ الدَّخول فحَوْملِ"
  - text: "سَلو قَلبي غَداةَ سَلا وَثابا لَعَلَّ عَلى الجَمالِ لَهُ عِتابا"
-datasets:
-- Yah216/autotrain-data-Poem_meter_3
 co2_eq_emissions: 404.66986451902227
 ---
 
@@ -13,21 +11,24 @@ co2_eq_emissions: 404.66986451902227
 
 - Problem type: Multi-class Classification
 - CO2 Emissions (in grams): 404.66986451902227
-
+## Dataset
+We used the APCD dataset cited hereafter for pretraining the model. The dataset has been cleaned and only the main text and the meter columns were kept:
+```
+@Article{Yousef2019LearningMetersArabicEnglish-arxiv,
+  author =       {Yousef, Waleed A. and Ibrahime, Omar M. and Madbouly, Taha M. and Mahmoud,
+                  Moustafa A.},
+  title =        {Learning Meters of Arabic and English Poems With Recurrent Neural Networks: a Step
+                  Forward for Language Understanding and Synthesis},
+  journal =      {arXiv preprint arXiv:1905.05700},
+  year =         2019,
+  url =          {https://github.com/hci-lab/LearningMetersPoems}
+}
+```
 ## Validation Metrics
 
 - Loss: 0.21315555274486542
 - Accuracy: 0.9493554089595999
 - Macro F1: 0.7537353091512587
-- Micro F1: 0.9493554089595999
-- Weighted F1: 0.9480607076301577
-- Macro Precision: 0.7925160467633223
-- Micro Precision: 0.9493554089595999
-- Weighted Precision: 0.9477713919153736
-- Macro Recall: 0.7352339804511467
-- Micro Recall: 0.9493554089595999
-- Weighted Recall: 0.9493554089595999
-
 
 ## Usage