Update README.md
Browse files
README.md
CHANGED
|
@@ -3,6 +3,26 @@ library_name: transformers
|
|
| 3 |
tags: []
|
| 4 |
---
|
| 5 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
# Model Card for Model ID
|
| 7 |
|
| 8 |
<!-- Provide a quick summary of what the model is/does. -->
|
|
|
|
| 3 |
tags: []
|
| 4 |
---
|
| 5 |
|
| 6 |
+
# Tutor Moves - Math Remediation: Affirm Student’s Correct Attempt
|
| 7 |
+
|
| 8 |
+
The tutor affirms the student’s correct attempt.
|
| 9 |
+
|
| 10 |
+
## Message Structure
|
| 11 |
+
|
| 12 |
+
Tutor CoPilot models are trained on a message structure of 10 context messages followed by one target message with the special tokens `[PRETEXT]` and `[TEXT]` used to demarcate the context and target messages. Messages are formatted as `{speaker}: {message}`, where the speaker is one of `tutor` or `student`, and the message is a lowercased, anonymized version of the message. Names are anonymized with [Edu-ConvoKit](https://edu-convokit.readthedocs.io/en/latest/preprocessing.html#edu_convokit.preprocessors.TextPreprocessor.anonymize_known_names), replacing student and tutor names with `[student]` and `[tutor]`, respectively. Models are trained on text with the structure
|
| 13 |
+
```
|
| 14 |
+
"[PRETEXT] {context} [TEXT] {target}"
|
| 15 |
+
```
|
| 16 |
+
Tutor CoPilot models are only trained with tutor utterances as targets. A synthetic example of this structure, without the full 10 context utterances, is below.
|
| 17 |
+
```
|
| 18 |
+
[PRETEXT] tutor: hello, [student], happy to work with you today.
|
| 19 |
+
student: hi
|
| 20 |
+
tutor: today we will work on the topic "adding numbers"
|
| 21 |
+
...
|
| 22 |
+
student: the answer is 2. [TEXT] tutor: that's correct! 2 points.
|
| 23 |
+
```
|
| 24 |
+
|
| 25 |
+
|
| 26 |
# Model Card for Model ID
|
| 27 |
|
| 28 |
<!-- Provide a quick summary of what the model is/does. -->
|