Update README.md
Browse files
README.md
CHANGED
|
@@ -69,6 +69,10 @@ print(results)
|
|
| 69 |
|
| 70 |
Compare vs. the original [grammar-synthesis-large](https://huggingface.co/pszemraj/grammar-synthesis-large).
|
| 71 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 72 |
## Model description
|
| 73 |
|
| 74 |
The intent is to create a text2text language model that successfully completes "single-shot grammar correction" on a potentially grammatically incorrect text **that could have a lot of mistakes** with the important qualifier of **it does not semantically change text/information that IS grammatically correct.**
|
|
@@ -85,6 +89,7 @@ If trading a slight decrease in grammatical correction quality for faster infere
|
|
| 85 |
- model: `apache-2.0`
|
| 86 |
- this is **still a work-in-progress** and while probably useful for "single-shot grammar correction" in a lot of cases, **give the outputs a glance for correctness ok?**
|
| 87 |
|
|
|
|
| 88 |
## Use Cases
|
| 89 |
|
| 90 |
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:
|
|
@@ -105,6 +110,7 @@ Final response in 1294.857 s:
|
|
| 105 |
|
| 106 |
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. _Note that _SOME_ of these are not fixed, especially as they venture into domain-specific terminology (i.e. irregular timberland instead of Random Forest)._
|
| 107 |
|
|
|
|
| 108 |
|
| 109 |
## Citation info
|
| 110 |
|
|
|
|
| 69 |
|
| 70 |
Compare vs. the original [grammar-synthesis-large](https://huggingface.co/pszemraj/grammar-synthesis-large).
|
| 71 |
|
| 72 |
+
|
| 73 |
+
---
|
| 74 |
+
|
| 75 |
+
|
| 76 |
## Model description
|
| 77 |
|
| 78 |
The intent is to create a text2text language model that successfully completes "single-shot grammar correction" on a potentially grammatically incorrect text **that could have a lot of mistakes** with the important qualifier of **it does not semantically change text/information that IS grammatically correct.**
|
|
|
|
| 89 |
- model: `apache-2.0`
|
| 90 |
- this is **still a work-in-progress** and while probably useful for "single-shot grammar correction" in a lot of cases, **give the outputs a glance for correctness ok?**
|
| 91 |
|
| 92 |
+
|
| 93 |
## Use Cases
|
| 94 |
|
| 95 |
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:
|
|
|
|
| 110 |
|
| 111 |
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. _Note that _SOME_ of these are not fixed, especially as they venture into domain-specific terminology (i.e. irregular timberland instead of Random Forest)._
|
| 112 |
|
| 113 |
+
---
|
| 114 |
|
| 115 |
## Citation info
|
| 116 |
|