[go: up one dir, main page]

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.
Replacing spaCy’s Sentencizer with yasbd: From 55.4% to 98.9% Accuracy

Replacing spaCy’s Sentencizer with yasbd: From 55.4% to 98.9% Accuracy

1
Comments
7 min read
The 500x Data Gap: Why AI Makes 4x More Errors in Swahili Than English

The 500x Data Gap: Why AI Makes 4x More Errors in Swahili Than English

Comments
2 min read
Why I Built a 23,000+ Record Open Dataset for Gujarati AI

Why I Built a 23,000+ Record Open Dataset for Gujarati AI

Comments 1
2 min read
Fine-tuning MuRIL for Multilingual Citizen Grievance Classification (with all the bugs I hit)

Fine-tuning MuRIL for Multilingual Citizen Grievance Classification (with all the bugs I hit)

2
Comments 1
3 min read
How We Match Messy Human Requests to Real Local Businesses — Without Keyword Search

How We Match Messy Human Requests to Real Local Businesses — Without Keyword Search

Comments
5 min read
Digit Tokenization: Why Commas Fix LLM Arithmetic

Digit Tokenization: Why Commas Fix LLM Arithmetic

Comments
8 min read
How LLMs Work: Transformer, Attention & Next Token Prediction Explained

How LLMs Work: Transformer, Attention & Next Token Prediction Explained

Comments
4 min read
My Release Gate Passed. The Model It Shipped Answered 'Neutral' To Everything.

My Release Gate Passed. The Model It Shipped Answered 'Neutral' To Everything.

2
Comments 2
6 min read
Perceived Latency: The Invisible KPI Killing Voice Experiences

Perceived Latency: The Invisible KPI Killing Voice Experiences

Comments
3 min read
The Convergence of Linguistic Mimicry and Reward Optimization: An Analysis of the Mechanisms of Defensive Behavior in Large Language Models

The Convergence of Linguistic Mimicry and Reward Optimization: An Analysis of the Mechanisms of Defensive Behavior in Large Language Models

Comments
3 min read
A 110M-Parameter Model Instead of an LLM? Testing Japanese NLI Cross-Encoders on Real Conversation Logs

A 110M-Parameter Model Instead of an LLM? Testing Japanese NLI Cross-Encoders on Real Conversation Logs

Comments
5 min read
Cross-Lingual Entity Resolution: Why Your Knowledge Graph Has Four Samsungs

Cross-Lingual Entity Resolution: Why Your Knowledge Graph Has Four Samsungs

Comments
4 min read
Attention Sinks: Why Streaming LLMs Break When You Evict Token 0

Attention Sinks: Why Streaming LLMs Break When You Evict Token 0

Comments
6 min read
LingoBridge-AI: Simplifying Complex Medical Reports for Rural Patients

LingoBridge-AI: Simplifying Complex Medical Reports for Rural Patients

Comments
1 min read
PermitFlow — The Construction Compliance Autopilot 🏗️🤖

PermitFlow — The Construction Compliance Autopilot 🏗️🤖

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