Some Tutorials and in depth analysis of NLP's techniques / algorithms
- Sentiment Analysis with Logistic Regression
- Sentiment Analysis with Naive Bayes
-
Dataset: ArXiv from Kaggle
-
Binary classification: Scikit-learn's CountVectorizer + TfidfTransformer
-
Explainability Methods: LIME, SHAP
Useful references for explainibility methods:
- LIME --> Why Should I Trust You?": Explaining the Predictions of Any Classifier
- SHAP --> A Unified Approach to Interpreting Model Predictions
- Adversarial attacks (have you heard of?), i.e. how to fool algorithms --> Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods
-
Open Questions for you:
- How to deal with multiclass problems?
- Try to develop binary classification with abstracts instead of titles
- Try to develop the same pipeline with spaCy
- Vector Space Models
- Machine Translation and Document Search