Update README.md

README.md

@@ -31,12 +31,12 @@ This is a fine-tuned version of the pre-trained [RUDOLPH 2.7B model](https://hug
 
 The model was prepared as a baseline for FusionBrain Challenge 2.0 (as a part of AI Journey Contest 2022) and is a fine-tuned version of the pre-trained [RuDOLPH 2.7B model](https://huggingface.co/sberbank-ai/RUDOLPH-2.7B) using 6 tasks:
 
-* Text QA – [SberQUaD dataset](https://huggingface.co/datasets/sberquad).
-* Math QA – [DeepMind Mathematics Dataset](https://github.com/deepmind/mathematics_dataset).
-* Image Captioning – [COCO dataset](https://cocodataset.org/#home) (with automated translation).
-* Image Generation – [COCO dataset](https://cocodataset.org/#home) (with automated translation).
-* VQA – [COCO dataset](https://cocodataset.org/#home) with prepared question set.
-* Text Recognition in the Wild - [START](https://n-ws-f21jf.s3pd02.sbercloud.ru/b-ws-f21jf-ny6/FBC2/titw_dataset.zip) dataset (**S**yn**T**hesized and **A**nnotated dataset for **T**ext **R**ecognition) consisting of synthetic and real-world human-annotated data for text recognition task.
+* Text QA: on [SberQUaD dataset](https://huggingface.co/datasets/sberquad).
+* Math QA: on [DeepMind Mathematics Dataset](https://github.com/deepmind/mathematics_dataset).
+* Image Captioning: on [COCO dataset](https://cocodataset.org/#home) translated into Russian (MT).
+* Image Generation: on [COCO dataset](https://cocodataset.org/#home) translated into Russian (MT).
+* VQA: on [COCO dataset](https://cocodataset.org/#home) with prepared question set.
+* Text Recognition in the Wild: on [START](https://n-ws-f21jf.s3pd02.sbercloud.ru/b-ws-f21jf-ny6/FBC2/titw_dataset.zip) dataset (**S**yn**T**hesized and **A**nnotated dataset for **T**ext **R**ecognition) consisting of synthetic and real-world human-annotated data for text recognition task.
 
 # Details of architecture