Add a section on back-translation best practice, wrt to evaluation

[cleong110]

          possible write what `ham2pose` suggests, here.

maybe also need a note about back translation: that people use it (progressive transformers, sign llm), but the outputs are incoherent. this is because people train the backtranslation models on the translation model outputs, and not independently, as one should.

Originally posted by @AmitMY in #77 (comment)

[cleong110]

Possibly relevant here:

• On The Evaluation of Machine Translation SystemsTrained With Back-Translation https://www.semanticscholar.org/paper/On-The-Evaluation-of-Machine-Translation-With-Edunov-Ott/8b5b8bd0942d5f39d01c1f4b89d174fb3fde99cc
• Quality Estimation via Backtranslation at the WMT 2022 Quality
  Estimation Task https://aclanthology.org/2022.wmt-1.54.pdf could work perhaps
• https://www.semanticscholar.org/paper/Back-translation-practices-in-organizational-loss-Klotz-Swider/239bd4331238aefce113096554707aa4e853f272

[cleong110]

@inproceedings{huangFastHighQualitySign2021,
  title = {Towards {{Fast}} and {{High-Quality Sign Language Production}}},
  booktitle = {Proceedings of the 29th {{ACM International Conference}} on {{Multimedia}}},
  author = {Huang, Wencan and Pan, Wenwen and Zhao, Zhou and Tian, Qi},
  year = {2021},
  month = oct,
  series = {{{MM}} '21},
  pages = {3172--3181},
  publisher = {Association for Computing Machinery},
  address = {New York, NY, USA},
  doi = {10.1145/3474085.3475463},
  url = {https://doi.org/10.1145/3474085.3475463},
  urldate = {2024-06-19},
  isbn = {978-1-4503-8651-7}
}

has this to say:

[cleong110]

Which seems to suggest that the method is:

1. Generate poses
2. run the code from "Sign Language Transformers: Joint End-to-End Sign Language Recognition and Translation" on it
3. See the BLEU score, etc.

With the theory being that as you generate better, the SLT should get more accurate.

They don't train a backtranslation model themselves, that's independent