Adding GLUECoS Hinglish and Spanglish code-switching bemchmark

[yjernite]

Adding a Dataset

• Name: GLUECoS
• Description: a Microsoft Benchmark to evaluate code-switching for only two language pairs but a variety of tasks
• Paper: https://aclanthology.org/2020.acl-main.329/
• Data: https://github.com/microsoft/GLUECoS
• Motivation: We currently only have one other dataset for code-switching

Instructions to add a new dataset can be found here.

[Ishan-Kumar2]

Hi @yjernite I am interested in adding this dataset.
In the repo they have also added a code mixed MT task from English to Hinglish here. I think this could be a good dataset addition in itself and then I can add the rest of the GLUECoS tasks as one dataset. What do you think?