Update README.md

README.md

@@ -11,6 +11,8 @@ datasets:
 - mrbesher/tr-paraphrase-tatoeba
 - figenfikri/stsb_tr
 - nli_tr
+- ttc4900
+- turkish_product_reviews
 ---
 
 
@@ -115,7 +117,7 @@ Refer to the paper for more information.
 
 We didn't yet evaluate the model for biases in any way.
 
-We only performed finetuning for several understanding and generation tasks:
+However, we performed finetuning for several understanding and generation tasks:
 
 - Paraphrasing: TAT and OST ([source](https://aclanthology.org/2022.icnlsp-1.14.pdf))
 - Summarization and news title generation: [TRNews](https://dl.acm.org/doi/10.1007/s10579-021-09568-y) and [MLSUM](https://arxiv.org/pdf/2004.14900v1.pdf)
@@ -123,8 +125,8 @@ We only performed finetuning for several understanding and generation tasks:
 - Part of Speech tagging: Two Universal Dependencies Turkish Treebanks, [IMST](https://universaldependencies.org/treebanks/tr_imst/index.html), [BOUN](https://universaldependencies.org/treebanks/tr_boun/index.html).
 - Semantic Textual Similarity: [STSb-tr](https://doi.org/10.18653/v1/2021.gem-1.3)
 - Natural language inference: [NLI-TR](https://doi.org/10.18653/v1/2020.emnlp-main.662)
+- Text classification: [Product reviews](https://huggingface.co/datasets/turkish_product_reviews), [TTC4900](https://doi.org/10.5505/pajes.2018.15931), and [Tweet sentiments](https://ieeexplore.ieee.org/document/8554037)
 
-- 
 Refer to the paper for more information.
 
 ## Environmental Impact