---
title: "#nlp articles | Hashnode"
description: "Explore 1,163 articles tagged #nlp on Hashnode. Tutorials, guides, and how-tos from the community."
url: "https://hashnode.com/tag/nlp"
---

Tag

# #nlp

1,163 posts · 362 followers

[Samuel Tosin](https://hashnode.com/@SamuelAspirin) · [14h ago](https://hashnode.com/posts/build-nlp-pipeline-python-therapy-notes/6afba1044c9d975934925ee6)

### [How to Build an NLP Pipeline in Python to Analyze Therapy Progress Notes](https://freecodecamp.org/news/build-nlp-pipeline-python-therapy-notes?utm_source=hashnode&utm_medium=feed)

Therapy progress notes are written records of what happened during a therapy session. They may include what a client said, what the therapist observed, the topics discussed, and plans for the next ses

30 min read · [freecodecamp.org](https://freecodecamp.org/news/build-nlp-pipeline-python-therapy-notes?utm_source=hashnode&utm_medium=feed)

[Tushar Verma](https://hashnode.com/@1tushar) · [1d ago](https://hashnode.com/posts/how-rag-grew-up-part-1-the-open-book-exam/6afa52e8cbdc628a8c23e951)

### [How RAG Grew Up, Part 1: The Open-Book Exam](https://1tushar.hashnode.dev/how-rag-grew-up-part-1-the-open-book-exam?utm_source=hashnode&utm_medium=feed)

Part 1 of 3. This one covers 2017 to 2020, when search and text generation ended up inside the same model.

8 min read · [1tushar.hashnode.dev](https://1tushar.hashnode.dev/how-rag-grew-up-part-1-the-open-book-exam?utm_source=hashnode&utm_medium=feed)

[1](https://hashnode.com/posts/how-rag-grew-up-part-1-the-open-book-exam/6afa52e8cbdc628a8c23e951)

[Dustin Liang](https://hashnode.com/@dustinliang) · [22h ago](https://hashnode.com/posts/tfidfvectorizer-keyword-extraction-in-python-turning-company-descriptions-into-concept-tags/6afb311a0d1b6e54c073c5f6)

### [TfidfVectorizer Keyword Extraction in Python: Turning Company Descriptions into Concept Tags](https://dustinliang.hashnode.dev/tfidfvectorizer-keyword-extraction-in-python-turning-company-descriptions-into-concept-tags?utm_source=hashnode&utm_medium=feed)

Keyword extraction with scikit-learn's TfidfVectorizer looks like a two-liner: fit the vectorizer, sort each row, take the top terms. On a real corpus the first result is usually disappointing. You ge

10 min read · [dustinliang.hashnode.dev](https://dustinliang.hashnode.dev/tfidfvectorizer-keyword-extraction-in-python-turning-company-descriptions-into-concept-tags?utm_source=hashnode&utm_medium=feed)

[Fenil Kasundra](https://hashnode.com/@fenil431) · [4d ago](https://hashnode.com/posts/multi-language-ai-chatbot-development-strategy-tools/6af6e08d21e4a05a327ef6c7)

### [Multi-Language AI Chatbot Development: Strategy & Tools](https://fenilkasundra.hashnode.dev/multi-language-ai-chatbot-development-strategy-tools?utm_source=hashnode&utm_medium=feed)

Plan multi-language AI chatbot development with three architectures, a 6-step strategy, the 2026 tool stack & a checklist for choosing a development partner.

8 min read · [fenilkasundra.hashnode.dev](https://fenilkasundra.hashnode.dev/multi-language-ai-chatbot-development-strategy-tools?utm_source=hashnode&utm_medium=feed)

[Michał Z](https://hashnode.com/@sixfingers) · [5d ago](https://hashnode.com/posts/toktumi-2-en/6af4da49e9132b8921350837)

### [How to Build a Large Language Model from Scratch? Toktumi 2.0 – Part 2/3](https://sixfingers.hashnode.dev/toktumi-2-en?utm_source=hashnode&utm_medium=feed)

Toktumi 2.0 – a Polish-language LLM based on GPT-2. How to learn from the first training and do it better.

18 min read · [sixfingers.hashnode.dev](https://sixfingers.hashnode.dev/toktumi-2-en?utm_source=hashnode&utm_medium=feed)

[Min SiThu](https://hashnode.com/@itsmeminsithu) · [Nov 8](https://hashnode.com/posts/teaching-a-computer-myanmar-handwriting-why-the-dataset-has-to-come-first/6aeff8145b3d63b19ed93c25)

### [Teaching a Computer Myanmar Handwriting: Why the Dataset Has to Come First](https://itsmeminsithu.hashnode.dev/teaching-a-computer-myanmar-handwriting-why-the-dataset-has-to-come-first?utm_source=hashnode&utm_medium=feed)

To put it simply, everyone in AI says data is the new oil — but nobody tells you what to do when there is no oil. For Myanmar handwriting, there is no clean, ready-made dataset a model can learn from.

6 min read · [itsmeminsithu.hashnode.dev](https://itsmeminsithu.hashnode.dev/teaching-a-computer-myanmar-handwriting-why-the-dataset-has-to-come-first?utm_source=hashnode&utm_medium=feed)

[Min SiThu](https://hashnode.com/@itsmeminsithu) · [Nov 7](https://hashnode.com/posts/what-temperature-does-in-a-language-model/6aeedd202ffbe1fb6731b164)

### [What Temperature Does in a Language Model](https://itsmeminsithu.hashnode.dev/what-temperature-does-in-a-language-model?utm_source=hashnode&utm_medium=feed)

To put it simply, temperature is a dial that decides how brave a language model is allowed to be when it picks its next word. Turn it down and the model plays safe, choosing the word it believes in mo

8 min read · [itsmeminsithu.hashnode.dev](https://itsmeminsithu.hashnode.dev/what-temperature-does-in-a-language-model?utm_source=hashnode&utm_medium=feed)

[Min SiThu](https://hashnode.com/@itsmeminsithu) · [Nov 7](https://hashnode.com/posts/how-sentiment-analysis-reads-feelings-in-text/6aeee3ecd9f584479afa1361)

### [How Sentiment Analysis Reads Feelings in Text](https://itsmeminsithu.hashnode.dev/how-sentiment-analysis-reads-feelings-in-text?utm_source=hashnode&utm_medium=feed)

To put it simply, sentiment analysis is a program that reads a piece of text and hands back a verdict on its mood: positive, negative, or somewhere in between. It does not understand your feelings. It

8 min read · [itsmeminsithu.hashnode.dev](https://itsmeminsithu.hashnode.dev/how-sentiment-analysis-reads-feelings-in-text?utm_source=hashnode&utm_medium=feed)

[Min SiThu](https://hashnode.com/@itsmeminsithu) · [Nov 7](https://hashnode.com/posts/why-tokenization-is-harder-for-the-myanmar-language/6aeee14eb36743306a426c45)

### [Why Tokenization Is Harder for the Myanmar Language](https://itsmeminsithu.hashnode.dev/why-tokenization-is-harder-for-the-myanmar-language?utm_source=hashnode&utm_medium=feed)

To put it simply, every language model reads text through a chopping step that was mostly trained on English — and Myanmar text walks into that chopper with no spaces, stacked letters, and extra marks

9 min read · [itsmeminsithu.hashnode.dev](https://itsmeminsithu.hashnode.dev/why-tokenization-is-harder-for-the-myanmar-language?utm_source=hashnode&utm_medium=feed)

[Min SiThu](https://hashnode.com/@itsmeminsithu) · [Nov 7](https://hashnode.com/posts/what-is-the-difference-between-fine-tuning-prompting-and-rag/6aeedf538451545ba7bbecb2)

### [What Is the Difference Between Fine-Tuning, Prompting, and RAG](https://itsmeminsithu.hashnode.dev/what-is-the-difference-between-fine-tuning-prompting-and-rag?utm_source=hashnode&utm_medium=feed)

To put it simply, all three are ways to make a general model useful for your own material, and the real difference is where the change happens. Prompting changes what you say to the model. RAG changes

9 min read · [itsmeminsithu.hashnode.dev](https://itsmeminsithu.hashnode.dev/what-is-the-difference-between-fine-tuning-prompting-and-rag?utm_source=hashnode&utm_medium=feed)
