Update README.md
Browse files
README.md
CHANGED
|
@@ -78,7 +78,7 @@ Compare some of the heavier-error examples on [other grammar correction models](
|
|
| 78 |
Obviously, this section is quite general as there are many things one can use "general single-shot grammar correction" for. Some ideas or use cases:
|
| 79 |
|
| 80 |
1. Correcting highly error-prone LM outputs. Some examples would be audio transcription (ASR) (this is literally some of the examples) or something like handwriting OCR.
|
| 81 |
-
|
| 82 |
2. Correcting/infilling text generated by text generation models to be cohesive/remove obvious errors that break the conversation immersion. I use this on the outputs of [this OPT 2.7B chatbot-esque model of myself](https://huggingface.co/pszemraj/opt-peter-2.7B).
|
| 83 |
> TODO add an example
|
| 84 |
3. Somewhat related to #2 above, fixing/correcting so-called [tortured-phrases](https://arxiv.org/abs/2107.06751) that are dead giveaways text was generated by a language model.
|
|
|
|
| 78 |
Obviously, this section is quite general as there are many things one can use "general single-shot grammar correction" for. Some ideas or use cases:
|
| 79 |
|
| 80 |
1. Correcting highly error-prone LM outputs. Some examples would be audio transcription (ASR) (this is literally some of the examples) or something like handwriting OCR.
|
| 81 |
+
- To be investigated further, depending on what model/system is used it _might_ be worth it to apply this after OCR on typed characters.
|
| 82 |
2. Correcting/infilling text generated by text generation models to be cohesive/remove obvious errors that break the conversation immersion. I use this on the outputs of [this OPT 2.7B chatbot-esque model of myself](https://huggingface.co/pszemraj/opt-peter-2.7B).
|
| 83 |
> TODO add an example
|
| 84 |
3. Somewhat related to #2 above, fixing/correcting so-called [tortured-phrases](https://arxiv.org/abs/2107.06751) that are dead giveaways text was generated by a language model.
|