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.
minbpe vs turboBPE: Two ways to think about tokenizer training

minbpe vs turboBPE: Two ways to think about tokenizer training

Comments
4 min read
Replacing Cross-Encoder Reranking with a Weighted Hybrid Score

Replacing Cross-Encoder Reranking with a Weighted Hybrid Score

Comments
5 min read
Building a Voice AI Platform with 28 Modules in Python

Building a Voice AI Platform with 28 Modules in Python

Comments
1 min read
When translation gives you one answer and no context

When translation gives you one answer and no context

Comments
2 min read
Moroccan Darija in NLP: Challenges and Opportunities

Moroccan Darija in NLP: Challenges and Opportunities

3
Comments
5 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
LLM Self-Preference Bias: How Anonymized Peer Review Fixes It

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

Comments
7 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
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.