Natural language processing

ColBERT (Contextualized Late Interaction over BERT) is a retrieval model that is designed to strike a balance between the efficiency of traditional methods like BM25 and the accuracy of deep learning models like BERT, an open source deep learning model used for natural language understanding. ColBERT uses the late interaction and MaxSim scoring method to rank the documents based on their relevance to the query. This scoring method furnishes better retrieval because of fine-grained matching and context awareness.

Get an introduction to natural language processing and learn how it can help us to converse more naturally with computers.

Learn how to create a LangChain RAG system in Python with watsonx. Fetch 27 articles from a website to create a vector store as context for an LLM to answer questions about the topic.

Create a specialised LLM using the Low-Rank Adaption (LoRA) transformer technique and Optuna library for a question answering task

Use tokenizers from the Python NLTK to complete a standard text normalization technique

Use watsonx, NLTK, and spaCy to prepare raw text data for use in ML models and NLP tasks