Update README.md

README.md

@@ -1,7 +1,7 @@
 ---
 license: mit
 language:
-- en
+- multilingual
 library_name: transformers
 pipeline_tag: text-classification
 widget:
@@ -12,9 +12,25 @@ widget:
 - text: "You wont believe what happened to me today :)"
 - text: "You wont believe what happened to me today :("
 ---
-This is an emotion classification model based on finetuning of a Berince model (describe) on self-labeled emotion dataset (Lykousas et al., 2019) in English that corresponds to Anger, Fear, Sadness, Joy, and Affection. 
+This is an emotion classification model based on finetuning of a Bernice model (a multilingual pre-trained model trained on multilingual Twitter data) on self-labeled emotion dataset (Lykousas et al., 2019) in English that corresponds to Anger, Fear, Sadness, Joy, and Affection. 
 See the paper, [LEIA: Linguistic Embeddings for the Identification of Affect](https://arxiv.org/abs/2304.10973) for further details. 
 
+## Evaluation
+We evaluated LEIA-multilingual on Vent posts with self-annotated emotion labels that was identified (using an ensemble of language identefication tools) to be non-English. 
+See the below for the macro-F1 scores across emotion categories and languages:
+
+language | Macro-F1
+ar |	44.18[43.07,45.29] 
+da 	|65.44[60.96,69.83] 
+de 	|60.47[57.58,63.38] 
+es 	|61.67[60.79,62.55] 
+fi 	|45.1[40.96,49.14] 
+fr 	|65.78[63.19,68.36] 
+it 	|63.37[59.67,67.1] 
+pt 	|57.27[55.15,59.4] 
+tl 	|58.37[55.51,61.23] 
+tr 	|45.42[41.17,49.79]
+
 
 ## Citation
 Please cite the following paper if you find the model useful for your work: