Update README.md

README.md

@@ -1,6 +1,34 @@
 ---
+pipeline_tag: sentence-similarity
 tags:
-- mteb
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+language: en
+license: apache-2.0
+datasets:
+- s2orc
+- flax-sentence-embeddings/stackexchange_xml
+- ms_marco
+- gooaq
+- yahoo_answers_topics
+- code_search_net
+- search_qa
+- eli5
+- snli
+- multi_nli
+- wikihow
+- natural_questions
+- trivia_qa
+- embedding-data/sentence-compression
+- embedding-data/flickr30k-captions
+- embedding-data/altlex
+- embedding-data/simple-wiki
+- embedding-data/QQP
+- embedding-data/SPECTER
+- embedding-data/PAQ_pairs
+- embedding-data/WikiAnswers
+- tum-nlp/cannot-dataset
 model-index:
 - name: all-mpnet-base-v2-negation
   results:
@@ -733,4 +761,98 @@ model-index:
       value: 84.77197321507954
     - type: max_f1
       value: 76.91440595175472
----
+---
+
+# all-mpnet-base-v2-negation
+This is a fine-tuned [sentence-transformers](https://www.SBERT.net) model to perform better with negated pairs of sentences.
+
+It maps sentences and paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
+
+## Usage (Sentence-Transformers)
+Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
+
+```
+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('dmlls/all-mpnet-base-v2-negation')
+embeddings = model.encode(sentences)
+print(embeddings)
+```
+
+## 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
+import torch.nn.functional as F
+
+#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)
+
+
+# Sentences we want sentence embeddings for
+sentences = ['This is an example sentence', 'Each sentence is converted']
+
+# Load model from HuggingFace Hub
+tokenizer = AutoTokenizer.from_pretrained('dmlls/all-mpnet-base-v2-negation')
+model = AutoModel.from_pretrained('dmlls/all-mpnet-base-v2-negation')
+
+# 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
+sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
+
+# Normalize embeddings
+sentence_embeddings = F.normalize(sentence_embeddings, p=2, dim=1)
+
+print("Sentence embeddings:")
+print(sentence_embeddings)
+```
+
+------
+
+## Background
+
+This model was finetuned within the context of the [*This is not correct! Negation-aware Evaluation of Language Generation Systems*](https://arxiv.org/abs/2307.13989) paper.
+
+
+## Intended uses
+
+Our model is intended to be used as a sentence and short paragraph encoder, performing well (i.e., reporting lower similarity scores) on negated pairs of sentences when compared to its base model.
+
+Given an input text, it outputs a vector which captures the semantic information. The sentence vector may be used for information retrieval, clustering or sentence similarity tasks.
+
+By default, input text longer than 384 word pieces is truncated.
+
+
+## Training procedure
+
+### Pre-training 
+
+We used [`sentence-transformers/all-mpnet-base-v2`](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) as base model.
+
+### Fine-tuning 
+
+We fine-tuned the model on the [CANNOT dataset](https://huggingface.co/datasets/tum-nlp/cannot-dataset) using a contrastive objective. Formally, we compute the cosine similarity from each possible sentence pairs from the batch. We then apply the cross entropy loss by comparing with true pairs.
+
+#### Hyper parameters
+We followed an analogous approach to [how other Sentence Transformers were trained](https://github.com/UKPLab/sentence-transformers/blob/3e1929fddef16df94f8bc6e3b10598a98f46e62d/examples/training/nli/training_nli_v2.py).
+
+We took the first 90% of samples from the CANNOT dataset as the training split.
+
+We used a batch size of 64 and trained for 1 epoch.