Limit deployments to main

.drone.yml

@@ -4,6 +4,9 @@ name: update_website
 steps:
    - name: hugo_build
      image: alombarte/hugo
+     when:
+      branch:
+       - main
      commands:
        - git submodule init
        - git submodule update
@@ -11,6 +14,9 @@ steps:
        - hugo
    - name: hugo_publish
      image: alpine:3.12.3
+     when:
+      branch:
+       - main
      environment:
       FTP_USERNAME:
         from_secret: FTP_USERNAME

brainsteam/content/posts/2021-01-02-nlp-model-rationale/index.md

@@ -0,0 +1,27 @@
+---
+title: Explain Yourself! Self-Rationalizing NLP Models
+author: James
+type: post
+draft: true
+resources:
+ - name: feature
+   src: images/feature.jpg
+date: 2021-01-02T16:47:02+00:00
+url: /2021/01/02/rationalizing-nlp-classifications/
+description: We examine a recent technique for enabling existing NLP models to provide human-readable rationales of why they made a decision.
+categories:
+  - PhD
+  - Academia
+  - Open Source
+tags:
+  - machine-learning
+  - python
+  - ai
+  - nlp
+  - spacy
+
+---
+
+The ability to understand and rationalise about automated decisions is becoming particularly important as more and more businesses adopt AI into their core processes. Particularly in light of legislation like GDPR requiring subjects of automated decisions to be given the right to an explanation as to why that decision was made. There have been a number of breakthroughs in explainable models in the last few years as academic teams in the machine learning space focus their attention on the why and the how.
+
+Significant breakthroughs in model explainability were seen in the likes of [LIME](https://towardsdatascience.com/understanding-model-predictions-with-lime-a582fdff3a3b) and [SHAP](https://towardsdatascience.com/explain-your-model-with-the-shap-values-bc36aac4de3d) where local surrogate models, which are explainable but only for the small number of data samples under observation, are used to approximate the importance/contribution of features to a particular decision.