From pipelines to prompts

NLP in the LLM era

Traditional natural language processing (NLP) relied on task-specific pipelines (for sentiment analysis, entities recognition, topic modelling, etc.) and massive labeled datasets. Today, a single pre-trained large language model (LLM) can handle all tasks through plain-language prompts.

But is a generative model always the right tool for the job?

In this webinar, I will compare the results, data constraints, and compute requirements of running the same tasks on the same corpus through three eras of NLP: the classic pipeline, text embeddings, and prompting a small LLM. We will see that embeddings remain a practical and efficient choice for semantic search and classification, especially on smaller datasets.

Coming up on October 27.