update README
Browse files
README.md
CHANGED
@@ -59,7 +59,7 @@ Downloading builder script: 100%|βββββββββββββββ
|
|
59 |
The [Expectation-Adjusted-Distinct paper](https://aclanthology.org/2022.acl-short.86) (Liu and Sabour et al. 2022) compares Expectation-Adjusted-Distinct scores of ten different methods with the original Distinct. These scores get higher human correlation from 0.56 to 0.65.
|
60 |
|
61 |
### Examples
|
62 |
-
Example of
|
63 |
```python
|
64 |
>>> my_new_module = evaluate.load("lsy641/distinct")
|
65 |
>>> results = my_new_module.compute(references=["Hi.", "I'm sorry to hear that", "I don't know"], vocab_size=50257)
|
@@ -73,7 +73,7 @@ Example of calculate Expectation-Adjusted-Distinct byy giving voab_size or data
|
|
73 |
```
|
74 |
|
75 |
|
76 |
-
Example of
|
77 |
```python
|
78 |
>>> my_new_module = evaluate.load("lsy641/distinct")
|
79 |
>>> results = my_new_module.compute(references=["Hi.", "I'm sorry to hear that", "I don't know"], mode="Distinct")
|
|
|
59 |
The [Expectation-Adjusted-Distinct paper](https://aclanthology.org/2022.acl-short.86) (Liu and Sabour et al. 2022) compares Expectation-Adjusted-Distinct scores of ten different methods with the original Distinct. These scores get higher human correlation from 0.56 to 0.65.
|
60 |
|
61 |
### Examples
|
62 |
+
Example of calculating Expectation-Adjusted-Distinct, given either voab_size or data for vocab_size calculation. Besides returning Expectation-Adjusted-Distinct, this mode will also return Distinct-1, 2, and 3.
|
63 |
```python
|
64 |
>>> my_new_module = evaluate.load("lsy641/distinct")
|
65 |
>>> results = my_new_module.compute(references=["Hi.", "I'm sorry to hear that", "I don't know"], vocab_size=50257)
|
|
|
73 |
```
|
74 |
|
75 |
|
76 |
+
Example of calculating original Distinct. This will return Distinct-1,2,and 3.
|
77 |
```python
|
78 |
>>> my_new_module = evaluate.load("lsy641/distinct")
|
79 |
>>> results = my_new_module.compute(references=["Hi.", "I'm sorry to hear that", "I don't know"], mode="Distinct")
|