Update from earendil

README.md

@@ -1,25 +1,32 @@
 ---
-language: el
-pipeline_tag: zero-shot-classification
+language: 
+ -el
+ -en
+
 tags:
 - xlm-roberta-base
 datasets:
 - multi_nli
 - snli
 - allnli_greek
+
 metrics:
 - accuracy
-license: apache-2.0
+pipeline_tag: zero-shot-classification
 widget:
 - text: "Το Facebook κυκλοφόρησε τα πρώτα «έξυπνα» γυαλιά επαυξημένης πραγματικότητας"
   candidate_labels: "πολιτική, τεχνολογία, αθλητισμός"
+  multi_class: false
+license: apache-2.0
 ---
 
 # Cross-Encoder for Greek Natural Language Inference (Textual Entailment) & Zero-Shot Classification 
+## By the Hellenic Army Academy (SSE) and the Technical University of Crete (TUC)
+
 This model was trained using [SentenceTransformers](https://sbert.net) [Cross-Encoder](https://www.sbert.net/examples/applications/cross-encoder/README.html) class.
-#### By the
+
 ## Training Data
-The model was trained on the the Greek version of the combined AllNLI dataset([SNLI](https://nlp.stanford.edu/projects/snli/) and [MultiNLI](https://cims.nyu.edu/~sbowman/multinli/)) which was created using EN2EL NMT model available [here](https://huggingface.co/lighteternal/SSE-TUC-mt-en-el-cased).
+The model was trained on the the combined Greek+English version of the AllNLI dataset(sum of [SNLI](https://nlp.stanford.edu/projects/snli/) and [MultiNLI](https://cims.nyu.edu/~sbowman/multinli/)). The Greek part was created using the EN2EL NMT model available [here](https://huggingface.co/lighteternal/SSE-TUC-mt-en-el-cased).
 
 The model can be used in two ways:
 * NLI/Textual Entailment: For a given sentence pair, it will output three scores corresponding to the labels: contradiction, entailment, neutral.
@@ -28,6 +35,7 @@ The model can be used in two ways:
 ## Performance
 
 Evaluation on classification accuracy (entailment, contradiction, neutral) on mixed (Greek+English) AllNLI-dev set:
+
 | Metric | Value |
 | --- | --- |
 | Accuracy | 0.8409 |
@@ -41,7 +49,7 @@ Evaluation on classification accuracy (entailment, contradiction, neutral) on mi
 Pre-trained models can be used like this:
 ```python
 from sentence_transformers import CrossEncoder
-model = CrossEncoder('MODEL_NAME')
+model = CrossEncoder('lighteternal/nli-xlm-r-greek')
 scores = model.predict([('Δύο άνθρωποι συναντιούνται στο δρόμο', 'Ο δρόμος έχει κόσμο'),
                         ('Ένα μαύρο αυτοκίνητο ξεκινάει στη μέση του πλήθους.', 'Ένας άντρας οδηγάει σε ένα μοναχικό δρόμο'), 
                         ('Δυο γυναίκες μιλάνε στο κινητό', 'Το τραπέζι ήταν πράσινο')])
@@ -64,8 +72,8 @@ You can use the model also directly with Transformers library (without SentenceT
 from transformers import AutoTokenizer, AutoModelForSequenceClassification
 import torch
 
-model = AutoModelForSequenceClassification.from_pretrained('MODEL_NAME')
-tokenizer = AutoTokenizer.from_pretrained('MODEL_NAME')
+model = AutoModelForSequenceClassification.from_pretrained('lighteternal/nli-xlm-r-greek')
+tokenizer = AutoTokenizer.from_pretrained('lighteternal/nli-xlm-r-greek')
 
 features = tokenizer(['Δύο άνθρωποι συναντιούνται στο δρόμο', 'Ο δρόμος έχει κόσμο'], 
                     ['Ένα μαύρο αυτοκίνητο ξεκινάει στη μέση του πλήθους.', 'Ένας άντρας οδηγάει σε ένα μοναχικό δρόμο.'],  
@@ -84,7 +92,7 @@ This model can also be used for zero-shot-classification:
 ```python
 from transformers import pipeline
 
-classifier = pipeline("zero-shot-classification", model='MODEL_NAME')
+classifier = pipeline("zero-shot-classification", model='lighteternal/nli-xlm-r-greek')
 
 sent = "Το Facebook κυκλοφόρησε τα πρώτα «έξυπνα» γυαλιά επαυξημένης πραγματικότητας"
 candidate_labels = ["πολιτική", "τεχνολογία", "αθλητισμός"]
@@ -98,4 +106,3 @@ The research work was supported by the Hellenic Foundation for Research and Inno
 Citation for the Greek model TBA.
 Based on the work [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084)
 Kudos to @nreimers (Nils Reimers) for his support on Github . 
-