Update README.md

README.md

@@ -15,8 +15,9 @@ datasets:
 - xnli
 pipeline_tag: zero-shot-classification
 widget:
-- text: "Såframt uforutsette ting ikke inntreffer, kommer statsministeren til å presentere en plan for gjenåpningen av samfunnet før påske. Det bekrefter hun overfor Dagbladet."
-  candidate_labels: "politikk, helse, sport, religion, geografi"
+- text: "Folkehelseinstituttets mest optimistiske anslag er at alle over 18 år er ferdigvaksinert innen midten av september."
+  candidate_labels: "politikk, helse, sport, religion"
+  hypothesis_template = "Denne teksten handler om {}."
   multi_class: true
 ---
 
@@ -25,15 +26,34 @@ widget:
 # NB-Bert base model finetuned on Norwegian machine translated MNLI
 
 ## Description
-
-This finetuned model was created to show that it is possible to use a MNLI finetuned model for zero-shot classification. It is an alternative to finetuning a model on a specific annotated dataset.
-
-## Intended use & limitations
-
-## Training data
+The most effective way of creating a good classifier is to finetune it for this specific task. However, in many cases this is simply impossible. 
+[Yin et al.](https://arxiv.org/abs/1909.00161) has proposed a very clever way of using pre-trained MNLI model as a zero-shot sequence classifiers. The methods works by reformulating the question to an MNLI hypothesis. If we want to figure out if a text is about "sport", we simply state that "This text is about sport" ("Denne teksten handler om sport").
+
+When the model is finetuned on the 400k large MNLI task, it is in many cases able to solve this classification tasks. There are no MNLI-set of this size in Norwegian but we have trained it on a machine translated version of the original MNLI-set.
+
+## Hugging Face zero-shot-classification pipeline
+The easiest way to try this out is using the Hugging Face pipeline. Please note that you will improve the results by overriding the English hypothesis template. 
+```python
+from transformers import pipeline
+classifier = pipeline("zero-shot-classification", model="NBAiLab/nb-bert-base-mnli")
+```
+You can then use this pipeline to classify sequences into any of the class names you specify.
+```python
+sequence_to_classify = "Folkehelseinstituttets mest optimistiske anslag er at alle over 18 år er ferdigvaksinert innen midten av september."
+candidate_labels = ["politikk, helse, sport, religion"]
+hypothesis_template = "Denne teksten handler om {}."
+classifier(sequence_to_classify, candidate_labels, hypothesis_template=hypothesis_template, multi_class=True)
+
+
+#{'labels': ['travel', 'dancing', 'cooking'],
+# 'scores': [0.9938651323318481, 0.0032737774308770895, 0.002861034357920289],
+# 'sequence': 'one day I will see the world'}
+```
 
 ## More information
 
 For more information on the model, see
 
 https://github.com/NBAiLab/notram
+
+Here you will also find a Colab explaining more in details how to use the zero-shot-classification pipeline.