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.
LLM Self-Preference Bias: How Anonymized Peer Review Fixes It

LLM Self-Preference Bias: How Anonymized Peer Review Fixes It

Comments
7 min read
How Self-Attention Works — QKV, Softmax, and Matrix Computation

How Self-Attention Works — QKV, Softmax, and Matrix Computation

Comments
5 min read
I Built an Open-Source Dataset of 985 Dream Symbols — Here's How You Can Use It

I Built an Open-Source Dataset of 985 Dream Symbols — Here's How You Can Use It

Comments
1 min read
Part 3 — Vector Retrieval in Domain-Specific Terminology Scenarios: From Model Selection to Dual Validation

Part 3 — Vector Retrieval in Domain-Specific Terminology Scenarios: From Model Selection to Dual Validation

1
Comments
10 min read
I Built an "Amazon-Style" AI Review Summarizer for Any Dataset (NLP, Transformers, Streamlit)

I Built an "Amazon-Style" AI Review Summarizer for Any Dataset (NLP, Transformers, Streamlit)

1
Comments 1
2 min read
How Attention Actually Works — From Next-Token Prediction to QKV Intuition

How Attention Actually Works — From Next-Token Prediction to QKV Intuition

Comments
3 min read
Tokenization under the hood: BPE, WordPiece, SentencePiece, and Unigram compared

Tokenization under the hood: BPE, WordPiece, SentencePiece, and Unigram compared

Comments
9 min read
From "I Understood Nothing" to Building a RAG App

From "I Understood Nothing" to Building a RAG App

Comments
7 min read
Fine-Tuning Large Language Models: A Practical Guide

Fine-Tuning Large Language Models: A Practical Guide

Comments
6 min read
How Transformer Architecture Works — Encoder, Decoder, Tokens, and Context

How Transformer Architecture Works — Encoder, Decoder, Tokens, and Context

Comments
6 min read
Smishi — an SMS phishing detector for Serbian/Bosnian/Croatian/Montenegrin

Smishi — an SMS phishing detector for Serbian/Bosnian/Croatian/Montenegrin

Comments
3 min read
I built an AI tool that saves 80% LLM costs & catches hallucinations (Open Source)

I built an AI tool that saves 80% LLM costs & catches hallucinations (Open Source)

Comments
2 min read
Yeni AI Modelleri ve EÄźitim

Yeni AI Modelleri ve EÄźitim

Comments
2 min read
Extracting structured data from messy text: what worked for me

Extracting structured data from messy text: what worked for me

1
Comments
3 min read
What embeddings are, explained by building one

What embeddings are, explained by building one

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