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.
word embeddings in NLP

word embeddings in NLP

Comments
2 min read
Word Embendding

Word Embendding

Comments
5 min read
"I Gave My FAQ Chatbot Word Embeddings. It Got Smarter, but Not the Way I Expected"

"I Gave My FAQ Chatbot Word Embeddings. It Got Smarter, but Not the Way I Expected"

1
Comments
4 min read
Wiper-Service-Agent explained

Wiper-Service-Agent explained

Comments
2 min read
Global-MMLU's Chinese and Korean world-history rows came shifted from OpenAI's MMMLU

Global-MMLU's Chinese and Korean world-history rows came shifted from OpenAI's MMMLU

Comments
4 min read
Why RAG breaks on Persian text, and what I built to fix it: normalization, half-spaces, spelling variants, and a regression bench

Why RAG breaks on Persian text, and what I built to fix it: normalization, half-spaces, spelling variants, and a regression bench

1
Comments 5
9 min read
When an MMLU answer key is wrong, "pick the longest answer" points to the experts' fix

When an MMLU answer key is wrong, "pick the longest answer" points to the experts' fix

Comments
3 min read
On MedMCQA, "pick the longest answer" beats chance, and EXCEPT questions only blunt it

On MedMCQA, "pick the longest answer" beats chance, and EXCEPT questions only blunt it

Comments
4 min read
MMLU-Pro's "pick the longest answer" shortcut survives translation into all 29 MMLU-ProX languages

MMLU-Pro's "pick the longest answer" shortcut survives translation into all 29 MMLU-ProX languages

Comments
3 min read
Ten of 45 models lose to "pick the longest answer" on 656 MMLU-Pro questions

Ten of 45 models lose to "pick the longest answer" on 656 MMLU-Pro questions

Comments
4 min read
Models follow MMLU-Pro's longest-answer cue too, and three score below it

Models follow MMLU-Pro's longest-answer cue too, and three score below it

Comments
4 min read
Parsing "2-3 cloves garlic, minced" is harder than it looks

Parsing "2-3 cloves garlic, minced" is harder than it looks

Comments
2 min read
Day 25: Bahdanau vs. Luong Attention

Day 25: Bahdanau vs. Luong Attention

Comments
5 min read
Picking the longest answer scores 67% on MMLU-Pro's STEM-website biology and psychology questions

Picking the longest answer scores 67% on MMLU-Pro's STEM-website biology and psychology questions

Comments
3 min read
Word Embeddings: How Machines Learn the Meaning Behind Words

Word Embeddings: How Machines Learn the Meaning Behind Words

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