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.
Dual Encoder vs Cross-Encoder: Why Your RAG Pipeline Needs Both

Dual Encoder vs Cross-Encoder: Why Your RAG Pipeline Needs Both

4
Comments
7 min read
How I Built Semantic Discussion Clustering Without Embeddings (and Why It Was Good Enough)

How I Built Semantic Discussion Clustering Without Embeddings (and Why It Was Good Enough)

Comments
2 min read
How LLMs Transform Writing Style: A Stylometric Experiment

How LLMs Transform Writing Style: A Stylometric Experiment

Comments
15 min read
Token Saving, and Caveman

Token Saving, and Caveman

Comments
7 min read
Day 8 - Sparse embedding - RAG

Day 8 - Sparse embedding - RAG

Comments
2 min read
I Built a Multilingual Spam Detection Dataset with 149K+ Messages Across 23 Languages

I Built a Multilingual Spam Detection Dataset with 149K+ Messages Across 23 Languages

5
Comments
4 min read
I Built Schedule Sensei & Pushed It to GitHub – Here's What's Inside (And I Need Your Help 👀)

I Built Schedule Sensei & Pushed It to GitHub – Here's What's Inside (And I Need Your Help 👀)

2
Comments
2 min read
I Self-Hosted an AI Assistant: Lessons from 48 Hours of Debugging

I Self-Hosted an AI Assistant: Lessons from 48 Hours of Debugging

Comments
2 min read
Hit 73% accuracy on the classifier, which is probably fine for now

Hit 73% accuracy on the classifier, which is probably fine for now

Comments
1 min read
# Starting My Journey into AI Research 🚀

# Starting My Journey into AI Research 🚀

1
Comments
1 min read
Luxury and nationalities, my first data science project!

Luxury and nationalities, my first data science project!

Comments
1 min read
Designing AI Companion Systems: What Makes Conversational Experiences Feel “Real”?

Designing AI Companion Systems: What Makes Conversational Experiences Feel “Real”?

1
Comments
2 min read
Retrieval accuracy falls roughly 50% when the answer sits in the middle of a long context window instead of at the edges

Retrieval accuracy falls roughly 50% when the answer sits in the middle of a long context window instead of at the edges

Comments
1 min read
How Transformers Architecture Powers Modern LLMs

How Transformers Architecture Powers Modern LLMs

Comments
8 min read
When Your Database Agent Speaks Plain English

When Your Database Agent Speaks Plain English

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