Want to interact with LLMs (Large Language Models) but perplexed on how to go about it and where to find good ones? You can of course interact with LLMs via search engines, but what if you want to build your own interaction agent? I got you covered in this article.

▲

What broadly distinguishes one domain from another? It is the named entities. It is essential to pick out entities from the text that you deal with for any useful NLP/NLU task.

In your NLP and Machine Learning tasks, as also research, getting the right detail from your voluminous text data is very important. You need a convenient, programmatic interface to your textual data.

▲

Using the right spellings shows good language skills. We often go wrong with our spellings and need a way to correct them. An automatic tool would help in this often overlooked task. North – a trie based spelling suggester helps you with some of your misspellings.

Follow a simple approach to specialize your model for a domain.

A template workflow with stable data trifurcation, custom loader with multi-level augmentation, CNN with variable learning rate and early stopping followed by the last mile decoding of the softmax output, and of course, evaluation.

Reviews and ratings are everywhere. But are reviews consistent with ratings?

This is an easy-to-use multilingual text summarizer with a command line and a web interface. It lets you experiment with text summarization.

We look at two contrasting case studies.

We build a Fake News Detection model using Spacy and Keras LSTM.