fix bold
Browse files
README.md
CHANGED
|
@@ -40,7 +40,7 @@ The primary task of this model is **Text Correction**, with a focus on:
|
|
| 40 |
|
| 41 |
This model is aimed to support processing user-generated content where informal language, abbreviations, and typos are prevalent, aiming to improve text clarity for further processing or human reading.
|
| 42 |
|
| 43 |
-
**Note - as of 15 March this model is really tuned to fix positional errors on a qwerty keyboard
|
| 44 |
|
| 45 |
## Usage
|
| 46 |
|
|
@@ -99,7 +99,6 @@ It has been training on
|
|
| 99 |
|
| 100 |
|
| 101 |
Then injecting typos from a range of places
|
| 102 |
-
- **Using NLPAUG** We've made some typos in Comm2 by usiing this library https://github.com/makcedward/nlpaug
|
| 103 |
- **Typo lists, Birkbeck, etc.**: These datasets contain lists of commonly misspelled words, making them invaluable for training models to recognize and correct spelling errors.
|
| 104 |
- Find these resources [here](https://www.dcs.bbk.ac.uk/~ROGER/corpora.html).
|
| 105 |
- **TOEFL Spell** A dataset of Spelling Annotations for English language learner essays written for TOEFL exams.
|
|
|
|
| 40 |
|
| 41 |
This model is aimed to support processing user-generated content where informal language, abbreviations, and typos are prevalent, aiming to improve text clarity for further processing or human reading.
|
| 42 |
|
| 43 |
+
**Note - as of 15 March this model is really tuned to fix positional errors on a qwerty keyboard.**
|
| 44 |
|
| 45 |
## Usage
|
| 46 |
|
|
|
|
| 99 |
|
| 100 |
|
| 101 |
Then injecting typos from a range of places
|
|
|
|
| 102 |
- **Typo lists, Birkbeck, etc.**: These datasets contain lists of commonly misspelled words, making them invaluable for training models to recognize and correct spelling errors.
|
| 103 |
- Find these resources [here](https://www.dcs.bbk.ac.uk/~ROGER/corpora.html).
|
| 104 |
- **TOEFL Spell** A dataset of Spelling Annotations for English language learner essays written for TOEFL exams.
|