Update README

README.md

@@ -1,50 +1,66 @@
 ---
-title: sbert_cosine
-datasets:
--  
-tags:
-- evaluate
-- metric
-description: "TODO: add a description here"
+title: Test Sbert Cosine
+emoji: ⚡
+colorFrom: purple
+colorTo: purple
 sdk: gradio
-sdk_version: 3.0.2
+sdk_version: 3.19.1
 app_file: app.py
 pinned: false
----
-
-# Metric Card for sbert_cosine
+tags:
+- evaluate
+- metric
+description: >-
+  Sbert cosine is a metric to score the semantic similarity of text generation tasks
+  
+  This is not the official implementation of cosine similarity using SBERT
 
-***Module Card Instructions:*** *Fill out the following subsections. Feel free to take a look at existing metric cards if you'd like examples.*
+  See the project at https://www.sbert.net/ for more information.
+---
 
-## Metric Description
-*Give a brief overview of this metric, including what task(s) it is usually used for, if any.*
+# Metric Card for SbertCosine
 
-## How to Use
-*Give general statement of how to use the metric*
+## Metric description
 
-*Provide simplest possible example for using the metric*
+Sbert cosine is a metric to score the semantic similarity of text generation tasks
 
-### Inputs
-*List all input arguments in the format below*
-- **input_field** *(type): Definition of input, with explanation if necessary. State any default value(s).*
+## How to use 
 
-### Output Values
+```python
+from evaluate import load
+sbert_cosine = load("transZ/sbert_cosine")
+predictions = ["hello there", "general kenobi"]
+references = ["hello there", "general kenobi"]
+results = sbert_cosine.compute(predictions=predictions, references=references, lang="en")
+```
 
-*Explain what this metric outputs and provide an example of what the metric output looks like. Modules should return a dictionary with one or multiple key-value pairs, e.g. {"bleu" : 6.02}*
+## Output values
 
-*State the range of possible values that the metric's output can take, as well as what in that range is considered good. For example: "This metric can take on any value between 0 and 100, inclusive. Higher scores are better."*
+Sbert cosine outputs a dictionary with the following values:
 
-#### Values from Popular Papers
-*Give examples, preferrably with links to leaderboards or publications, to papers that have reported this metric, along with the values they have reported.*
+`score`: Range from 0.0 to 1.0
 
-### Examples
-*Give code examples of the metric being used. Try to include examples that clear up any potential ambiguity left from the metric description above. If possible, provide a range of examples that show both typical and atypical results, as well as examples where a variety of input parameters are passed.*
+## Limitations and bias
 
-## Limitations and Bias
-*Note any known limitations or biases that the metric has, with links and references if possible.*
+The [official repo](https://github.com/UKPLab/sentence-transformers) showed that Sbert can capture the semantic of the sentence well
 
 ## Citation
-*Cite the source where this metric was introduced.*
 
-## Further References
-*Add any useful further references.*
+```bibtex
+@article{Reimers2019,
+archivePrefix = {arXiv},
+arxivId = {1908.10084},
+author = {Reimers, Nils and Gurevych, Iryna},
+doi = {10.18653/v1/d19-1410},
+eprint = {1908.10084},
+isbn = {9781950737901},
+journal = {EMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Proceedings of the Conference},
+pages = {3982--3992},
+title = {{Sentence-BERT: Sentence embeddings using siamese BERT-networks}},
+year = {2019}
+}
+```
+    
+## Further References 
+- [Official website](https://www.sbert.net/)
+

sbert_cosine.py

@@ -11,52 +11,52 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-"""TODO: Add a description here."""
+"""SBERT consime similarity metric."""
 
 import evaluate
 import datasets
+import torch
+import torch.nn as nn
 
-
-# TODO: Add BibTeX citation
 _CITATION = """\
-@InProceedings{huggingface:module,
-title = {A great new module},
-authors={huggingface, Inc.},
-year={2020}
+@article{Reimers2019,
+archivePrefix = {arXiv},
+arxivId = {1908.10084},
+author = {Reimers, Nils and Gurevych, Iryna},
+doi = {10.18653/v1/d19-1410},
+eprint = {1908.10084},
+isbn = {9781950737901},
+journal = {EMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Proceedings of the Conference},
+pages = {3982--3992},
+title = {{Sentence-BERT: Sentence embeddings using siamese BERT-networks}},
+year = {2019}
 }
 """
 
-# TODO: Add description of the module here
 _DESCRIPTION = """\
-This new module is designed to solve this great ML task and is crafted with a lot of care.
+Use SBERT to produce embedding and score the similarity by cosine similarity
 """
 
 
-# TODO: Add description of the arguments of the module here
 _KWARGS_DESCRIPTION = """
-Calculates how good are predictions given some references, using certain scores
+Calculates how semantic similarity are predictions given some references, using certain scores
 Args:
     predictions: list of predictions to score. Each predictions
         should be a string with tokens separated by spaces.
     references: list of reference for each prediction. Each
         reference should be a string with tokens separated by spaces.
 Returns:
-    accuracy: description of the first score,
-    another_score: description of the second score,
+    score: description of the first score,
 Examples:
     Examples should be written in doctest format, and should illustrate how
     to use the function.
 
-    >>> my_new_module = evaluate.load("my_new_module")
-    >>> results = my_new_module.compute(references=[0, 1], predictions=[0, 1])
+    >>> sbert_cosine = evaluate.load("transZ/sbert_cosine")
+    >>> results = my_new_module.compute(references=["Nice to meet you"], predictions=["It is my pleasure to meet you"])
     >>> print(results)
-    {'accuracy': 1.0}
+    {'score': 0.85}
 """
 
-# TODO: Define external resources urls if needed
-BAD_WORDS_URL = "http://url/to/external/resource/bad_words.txt"
-
-
 @evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)
 class sbert_cosine(evaluate.Metric):
     """TODO: Short description of my evaluation module."""
@@ -92,4 +92,4 @@ class sbert_cosine(evaluate.Metric):
         accuracy = sum(i == j for i, j in zip(predictions, references)) / len(predictions)
         return {
             "accuracy": accuracy,
-        }
+        }