DEV Community

Natural Language Processing

NLP is Natural Language Processing the technology behind Home assistants and search engines.

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
How to extract clean article text, author and date from news URLs

How to extract clean article text, author and date from news URLs

Comments
3 min read
AstaBrief 8B: How AllenAI Trained a Small Open Model to Generate Cited Scientific Reports

AstaBrief 8B: How AllenAI Trained a Small Open Model to Generate Cited Scientific Reports

Comments
5 min read
A word's frequency rank is not its difficulty: grading words for a placement test

A word's frequency rank is not its difficulty: grading words for a placement test

Comments
3 min read
Why the dialogues in my Japanese speaking trainer aren't made up

Why the dialogues in my Japanese speaking trainer aren't made up

Comments
6 min read
I Trained an Open Decision Model on a Free GPU in 46 Minutes. On My Tests, It Beat Laya.

I Trained an Open Decision Model on a Free GPU in 46 Minutes. On My Tests, It Beat Laya.

Comments
6 min read
A 3B model that beats a 7B: failure-driven orchestration on uncontaminated knowledge

A 3B model that beats a 7B: failure-driven orchestration on uncontaminated knowledge

1
Comments
6 min read
Teaching a Computer Word Meaning Without a Dictionary

Teaching a Computer Word Meaning Without a Dictionary

Comments
5 min read
Locally-Run AI Model for Multilingual PDF Data Extraction: Focus on Malayalam, Hindi, and English

Locally-Run AI Model for Multilingual PDF Data Extraction: Focus on Malayalam, Hindi, and English

Comments
9 min read
chunklet-py v3.0.0: a smaller install, a smarter chunker, and no more global state

chunklet-py v3.0.0: a smaller install, a smarter chunker, and no more global state

1
Comments
5 min read
AI Agents - Async Programming and Pytantic Data Validation

AI Agents - Async Programming and Pytantic Data Validation

Comments
2 min read
Decision models are English-first. I measured them in Japanese, then built one.

Decision models are English-first. I measured them in Japanese, then built one.

Comments
7 min read
My First Steps into Word Embeddings with Word2Vec

My First Steps into Word Embeddings with Word2Vec

Comments
2 min read
Voice-to-SQL: hablarle a tu base de datos con un LLM (y por qué la seguridad es lo difícil)

Voice-to-SQL: hablarle a tu base de datos con un LLM (y por qué la seguridad es lo difícil)

Comments 1
3 min read
What My Spam Classifier Couldn't See: A Beginner's Guide to Word Embeddings

What My Spam Classifier Couldn't See: A Beginner's Guide to Word Embeddings

Comments
5 min read
When LLMs don't know a Greek word, they make one up

Kaggle Benchmarking Challenge Submission

When LLMs don't know a Greek word, they make one up

Comments
5 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.