Update README.md

README.md

@@ -5,12 +5,17 @@ tags:
 - feature-extraction
 - sentence-similarity
 - transformers
+- MT Evaluation
+- Metrics
+- Evaluation
 
 ---
 
-# {MODEL_NAME}
+# {AnanyaCoder/XLsim_en-de}
 
-This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
+XLSim: MT Evaluation Metric based on Siamese Architecture
+
+XLsim is a supervised reference-based metric that regresses on human scores provided by WMT (2017-2022). Using a cross-lingual language model XLM-RoBERTa-base [ https://huggingface.co/xlm-roberta-base ] , we train a supervised model using a Siamese network architecture with CosineSimilarityLoss.
 
 <!--- Describe your model here -->
 
@@ -25,50 +30,29 @@ pip install -U sentence-transformers
 Then you can use the model like this:
 
 ```python
-from sentence_transformers import SentenceTransformer
-sentences = ["This is an example sentence", "Each sentence is converted"]
-
-model = SentenceTransformer('{MODEL_NAME}')
-embeddings = model.encode(sentences)
-print(embeddings)
-```
 
 
+from sentence_transformers import SentenceTransformer,losses, models, util
 
-## Usage (HuggingFace Transformers)
-Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
-
-```python
-from transformers import AutoTokenizer, AutoModel
-import torch
-
+metric_model = SentenceTransformer('{MODEL_NAME}')
 
-#Mean Pooling - Take attention mask into account for correct averaging
-def mean_pooling(model_output, attention_mask):
-    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
-    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
-    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
+#Compute embedding for both lists
+mt_samples = ['This is a mt sentence1','This is a mt sentence2']
+ref_samples = ['This is a ref sentence1','This is a ref sentence2']
 
+mtembeddings = metric_model.encode(mt_samples, convert_to_tensor=True)
+refembeddings = metric_model.encode(ref_samples, convert_to_tensor=True)
 
-# Sentences we want sentence embeddings for
-sentences = ['This is an example sentence', 'Each sentence is converted']
+#Compute cosine-similarities
+cosine_scores_refmt = util.cos_sim(mtembeddings, refembeddings)
+#cosine_scores_srcmt = util.cos_sim(mtembeddings, srcembeddings) #qe
+metric_model_scores = []
+for i in range(len(mt_samples)):
+    metric_model_scores.append(cosine_scores_refmt[i][i].tolist())
 
-# Load model from HuggingFace Hub
-tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
-model = AutoModel.from_pretrained('{MODEL_NAME}')
+scores = metric_model_scores
 
-# Tokenize sentences
-encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
 
-# Compute token embeddings
-with torch.no_grad():
-    model_output = model(**encoded_input)
-
-# Perform pooling. In this case, mean pooling.
-sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
-
-print("Sentence embeddings:")
-print(sentence_embeddings)
 ```
 
 
@@ -77,7 +61,7 @@ print(sentence_embeddings)
 
 <!--- Describe how your model was evaluated -->
 
-For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
+For an automated evaluation of this model, see: [WMT23 Metrics Shared Task findings](https://aclanthology.org/2023.wmt-1.51.pdf)
 
 
 ## Training
@@ -123,4 +107,8 @@ SentenceTransformer(
 
 ## Citing & Authors
 
-<!--- Describe where people can find more information -->
+<!--- Describe where people can find more information -->
+[MEE4 and XLsim : IIIT HYD’s Submissions’ for WMT23 Metrics Shared Task](https://aclanthology.org/2023.wmt-1.66) (Mukherjee & Shrivastava, WMT 2023)
+
+
+