Which NLP tasks are typically solved by AutoML?

AutoML is designed to automate the process of applying machine learning to real-world problems, particularly in the field of natural language processing (NLP). The correct answer highlights tasks that are commonly addressed using AutoML and showcases the versatility and focus of this technology in NLP applications.

Entity Extraction, also known as Named Entity Recognition (NER), involves identifying and classifying key components in text, such as names, dates, and locations, which are crucial for understanding context and meaning. Text Classification refers to the process of categorizing text into predefined categories based on its content, which is essential for many applications, such as spam detection and sentiment analysis. Sentiment Analysis involves gauging the emotional tone behind a body of text to determine opinions, attitudes, or feelings expressed within it—critical for businesses wanting to analyze customer feedback.

The other options include tasks that either do not align with typical uses of AutoML or involve processes that are not primarily focused on NLP. Image Classification is related to computer vision, while tasks like Data Normalization and Data Cleaning, while important for overall data preprocessing, do not directly represent specific NLP tasks that AutoML targets. Speech Recognition pertains to audio processing and is separate from textual analysis capabilities covered by AutoML in NLP. Thus, the inclusion