Update README.md
Browse files
README.md
CHANGED
@@ -13,21 +13,23 @@ Quick Links:
|
|
13 |
* [Dataset, training, and evaluation](https://github.com/golsun/DialogRPT)
|
14 |
* [Colab Notebook Demo](https://colab.research.google.com/drive/1cAtfkbhqsRsT59y3imjR1APw3MHDMkuV?usp=sharing)
|
15 |
|
16 |
-
We considered the following tasks and provided corresponding pretrained models.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
|
18 |
-
| Model card | Description |
|
19 |
-
| :-----------: | :----------- |
|
20 |
-
| | **Given a context and its two human responses, predict...** |
|
21 |
-
| [`microsoft/DialogRPT-updown`](https://huggingface.co/microsoft/DialogRPT-updown) | ... which gets more upvotes? |
|
22 |
-
| [`microsoft/DialogRPT-width`](https://huggingface.co/microsoft/DialogRPT-width) | ... which gets more direct replies? |
|
23 |
-
| [`microsoft/DialogRPT-depth`](https://huggingface.co/microsoft/DialogRPT-depth) | ... which gets longer follow-up thread? |
|
24 |
-
| | **Given a context and one human response, distinguish it with...** |
|
25 |
-
| [`microsoft/DialogRPT-human-vs-rand`](https://huggingface.co/microsoft/DialogRPT-human-vs-rand) | ... a random human response |
|
26 |
-
| [`microsoft/DialogRPT-human-vs-machine`](https://huggingface.co/microsoft/DialogRPT-human-vs-machine) | ... a machine generated response |
|
27 |
|
28 |
|
29 |
### Examples:
|
30 |
The `updown` score predicts how likely the response is getting upvoted.
|
|
|
31 |
|
32 |
| Context | Response | `updown` score |
|
33 |
| :------ | :------- | :------------: |
|
|
|
13 |
* [Dataset, training, and evaluation](https://github.com/golsun/DialogRPT)
|
14 |
* [Colab Notebook Demo](https://colab.research.google.com/drive/1cAtfkbhqsRsT59y3imjR1APw3MHDMkuV?usp=sharing)
|
15 |
|
16 |
+
We considered the following tasks and provided corresponding pretrained models. This page is for the `updown` task, and other model cards can be found in table below.
|
17 |
+
|
18 |
+
|Task | Description | Pretrained model |
|
19 |
+
| :------------- | :----------- | :-----------: |
|
20 |
+
| **Human feedback** | **given a context and its two human responses, predict...**|
|
21 |
+
| `updown` | ... which gets more upvotes? | (this model) |
|
22 |
+
| `width`| ... which gets more direct replies? | [model card](https://huggingface.co/microsoft/DialogRPT-width) |
|
23 |
+
| `depth`| ... which gets longer follow-up thread? | [model card](https://huggingface.co/microsoft/DialogRPT-width) |
|
24 |
+
| **Human-like** (human vs fake) | **given a context and one human response, distinguish it with...** |
|
25 |
+
| `human_vs_rand`| ... a random human response | [model card](https://huggingface.co/microsoft/DialogRPT-human-vs-rand) |
|
26 |
+
| `human_vs_machine`| ... a machine generated response | [model card](https://huggingface.co/microsoft/DialogRPT-human-vs-machine) |
|
27 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
28 |
|
29 |
|
30 |
### Examples:
|
31 |
The `updown` score predicts how likely the response is getting upvoted.
|
32 |
+
Examples below can be reproduced with this [Colab Notebook](https://colab.research.google.com/drive/1cAtfkbhqsRsT59y3imjR1APw3MHDMkuV?usp=sharing)
|
33 |
|
34 |
| Context | Response | `updown` score |
|
35 |
| :------ | :------- | :------------: |
|