Explainable AI for NLP: Decoding Black Box

Recent advancements in machine learning have sparked greater interest in previously understudied topics. As machine learning improves, experts are being pushed to understand and trace how algorithms get their results, how models think, and why the end outcome. It is also difficult to communicate the outcome to end customers and internal stakeholders such as sales and customer service without explaining the outcomes in simple language, especially using visualization. In specialized domains like law and medicine, it becomes vital to understand the machine learning output. The author talked about major categories, categorization, and techniques. Also, the author introduced a library called NlpExplainer for the same. Currently, it works only for classification and shap. Future work involves incorporating more tasks like QnA and summarization and implementing more techniques like LIME apart from Shap.The author introduced a library called NlpExplainer for XAI