Update README.md
Browse files
README.md
CHANGED
@@ -33,7 +33,8 @@ The model is used to generate clinical notes from doctor-patient conversation da
|
|
33 |
- When the input data is composed of very minimal character tokens or if input is very large it starts to hallucinate.
|
34 |
|
35 |
|
36 |
-
### TEST DATA Sample For Inference (More given in `test.txt`)
|
|
|
37 |
"Doctor: Hi there, I love that dress, very pretty!
|
38 |
Patient: Thank you for complementing a seventy-two-year-old patient.
|
39 |
Doctor: No, I mean it, seriously. Okay, so you were admitted here in May two thousand nine. You have a history of hypertension, and on June eighteenth two thousand nine you had bad abdominal pain diarrhea and cramps.
|
@@ -48,21 +49,23 @@ Doctor: Okay. Anything else any other symptoms?
|
|
48 |
Patient: Actually no. Everything's well.
|
49 |
Doctor: Great.
|
50 |
Patient: Yeah."
|
51 |
-
|
52 |
|
53 |
## Training and evaluation data
|
54 |
|
55 |
-
|
56 |
-
|
57 |
-
-
|
58 |
-
-
|
59 |
-
-
|
60 |
-
-
|
61 |
-
-
|
|
|
|
|
62 |
|
63 |
## Training procedure
|
64 |
|
65 |
-
The model was trained on 1201 training samples and 100 validation samples of the modified [MTS-Dialog]()
|
66 |
|
67 |
### Training hyperparameters
|
68 |
|
|
|
33 |
- When the input data is composed of very minimal character tokens or if input is very large it starts to hallucinate.
|
34 |
|
35 |
|
36 |
+
### TEST DATA Sample For Inference (More given in [`test.txt`](https://huggingface.co/har1/HealthScribe-Clinical_Note_Generator/blob/main/test.txt))
|
37 |
+
```
|
38 |
"Doctor: Hi there, I love that dress, very pretty!
|
39 |
Patient: Thank you for complementing a seventy-two-year-old patient.
|
40 |
Doctor: No, I mean it, seriously. Okay, so you were admitted here in May two thousand nine. You have a history of hypertension, and on June eighteenth two thousand nine you had bad abdominal pain diarrhea and cramps.
|
|
|
49 |
Patient: Actually no. Everything's well.
|
50 |
Doctor: Great.
|
51 |
Patient: Yeah."
|
52 |
+
```
|
53 |
|
54 |
## Training and evaluation data
|
55 |
|
56 |
+
The model achieves the following results on the evaluation set:
|
57 |
+
|
58 |
+
- **Loss:** 0.1562
|
59 |
+
- **Rouge1:** 54.3238
|
60 |
+
- **Rouge2:** 34.2678
|
61 |
+
- **Rougel:** 46.5847
|
62 |
+
- **Rougelsum:** 51.2214
|
63 |
+
- **Generation Length:** 77.04
|
64 |
+
|
65 |
|
66 |
## Training procedure
|
67 |
|
68 |
+
The model was trained on 1201 training samples and 100 validation samples of the modified [MTS-Dialog](https://huggingface.co/datasets/har1/MTS_Dialogue-Clinical_Note)
|
69 |
|
70 |
### Training hyperparameters
|
71 |
|