Awesome! To protect your privacy on HN, please email [email protected] and let me know whether you prefer getting on a call or keep things in writing. Looking forward to hearing from you!
I positioned myself as someone seeking help, and the bot came across like an HR person play-acting empathy and care, and couldn't wait for me to leave the office. It came down to (1) do your research, (2) make a list, (3) take courses, (4) be aware of barriers.
It's for anyone who wants to learn NLP such that they get (a) an understanding of what's going on under the hood and (b) knowledge of how to get stuff done.
So the ideal outcome is someone who gets an end-to-end view from theory/concept to implementation.
If someone just wants to learn how to use tools/frameworks, I'd stick to the Colab notebooks. If someone's already experienced in ML and wants to learn something NLP-specific, I'd skip around to see what's interesting.
Yeah, I can see that being the case for specialized domains. With state-of-the-art models widely available to the public, knowledge of the domain and its workflows, and fine-tuning models to suit the domain will probably be your edge.
You could start by looking into either multitask transformers or really general seq2seq models like T5. With T5, for example, it just learns to transform one text sequence into another. So you could fine-tune T5 to produce your target sequence, but rather than outputting an explicit Python list of tuples, it would output a string that looks like a sequence of tuples.
I agree. I think having linguistics knowledge can help especially in applied situations. Linguistics knowledge can help create fallback systems when an ML system fails, or help build rules to amplify or dampen the confidence of a response from an ML system, or aid in the engineering of a system (all that comes before or after the ML blackbox).
Sort of like an algorithmic trader knowing market microstructure intimately (versus only pure statistics).
Bender's book is NOT an end-to-end text though imo. It's more a central jumping off point. So you can read about a concept and if it sounds interesting, search more about it.
I published part one of my free NLP course. The course is intended to help anyone who knows Python and a bit of math go from the very basics all the way to today's mainstream models and frameworks.
I strive to balance theory and practice and so every module consists of detailed explanations and slides along with a Colab notebook (in most modules) putting the theory into practice.
In part one, we cover text preprocessing, how to turn text into numbers, and multiple ways to classify and search text using "classical" approaches. And along the way, we'll pick up useful bits on how to use tools such as spaCy and scikit-learn.