speed-comparison VS spaCy

For example, Java runs on the JVM (Java Virtual Machine) instead of running directly on the hardware, and it also has a garbage collector to handle memory management. Running on a virtual machine means your code is more abstracted: you only have to worry about the JVM and not about the platform you’re running on (since the JVM is the platform), and it’s more portable since your code can go on anything that runs the JVM. But running the JVM as an intermediate layer takes more computing power and so does running garbage collection, meaning that you experience a performance penalty. Here’s one benchmark I could find comparing the use of different programming languages to compute pi, in which Java took about 3x as long as C to complete the same task

Or you've got the speed comparisons (https://github.com/niklas-heer/speed-comparison) -- Python is probably something like 10% the speed of C/C++ (although, like I said, 99% of the time that's comparable to premature optimization).

Looks like a PR was merged yesterday to make the code more simd friendly https://github.com/niklas-heer/speed-comparison/pull/52

Sure, they could have chosen Python. But I doubt the language differences account for even a noticeable percentage of the slowness of Brew.

Hi Community, In this article, I will demonstrate below steps to create your own chatbot by using spaCy (spaCy is an open-source software library for advanced natural language processing, written in the programming languages Python and Cython):

SpaCy: An open-source library providing tools for advanced NLP tasks like tokenization, entity recognition, and part-of-speech tagging.

spaCy https://spacy.io/

In this article, I'm going to walk through a sentiment analysis project from start to finish, using open-source Amazon product reviews. However, using the same approach, you can easily implement mass sentiment analysis on your own products. We'll explore an approach to sentiment analysis with one of the most popular Python NLP packages: spaCy.

Spacy [0] is a state-of-art / easy-to-use NLP library from the pre-LLM era. This post is the Spacy founder's thoughts on how to integrate LLMs with the kind of problems that "traditional" NLP is used for right now. It's an advertisement for Prodigy [1], their paid tool for using LLMs to assist data labeling. That said, I think I largely agree with the premise, and it's worth reading the entire post.

The steps described in "LLM pragmatism" are basically what I see my data science friends doing — it's hard to justify the cost (money and latency) in using LLMs directly for all tasks, and even if you want to you'll need a baseline model to compare against, so why not use LLMs for dataset creation or augmentation in order to train a classic supervised model?

[0] https://spacy.io/

[1] https://prodi.gy/

spaCy

I chose spacy. Although it's not state of the art, it's very well established and stable.