DEV Community

Natural Language Processing

NLP is Natural Language Processing the technology behind Home assistants and search engines.

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Correct, Cited, and Two Years Out of Date: Measuring Version Leakage in RAG

Correct, Cited, and Two Years Out of Date: Measuring Version Leakage in RAG

Comments
2 min read
Your Vocabulary Coverage Report Needs a Denominator

Your Vocabulary Coverage Report Needs a Denominator

Comments
4 min read
When a benchmark's gold is NOT the annotator majority: two reproducible censuses on ANLI and ChaosNLI

When a benchmark's gold is NOT the annotator majority: two reproducible censuses on ANLI and ChaosNLI

Comments
4 min read
Day 39: T5 and the Text-to-Text Framework

Day 39: T5 and the Text-to-Text Framework

Comments
5 min read
Can you re-derive a benchmark's gold labels from its raw annotator votes? Two reproducible censuses on SNLI and MultiNLI

Can you re-derive a benchmark's gold labels from its raw annotator votes? Two reproducible censuses on SNLI and MultiNLI

Comments
4 min read
Turning spoken commands into safe actions: regex first, the language model second

Turning spoken commands into safe actions: regex first, the language model second

Comments
4 min read
When the annotation gives away the answer: three reproducible leakage censuses on OpenBookQA, SciQ and QASC

When the annotation gives away the answer: three reproducible leakage censuses on OpenBookQA, SciQ and QASC

Comments
4 min read
Your Lead Scoring Prompt Doesn't Need the Whole Row

Your Lead Scoring Prompt Doesn't Need the Whole Row

Comments
7 min read
Day 39: T5 and the Text-to-Text Framework

Day 39: T5 and the Text-to-Text Framework

Comments
5 min read
Do SNLI and MultiNLI share any examples? Ten reproducible censuses of gold-label integrity in NLI and QA benchmarks

Do SNLI and MultiNLI share any examples? Ten reproducible censuses of gold-label integrity in NLI and QA benchmarks

Comments
3 min read
Do Japanese and English Share Neurons? I Trained the Microscope to Check

Do Japanese and English Share Neurons? I Trained the Microscope to Check

Comments
2 min read
25 reproducible audits of the metrics and gold labels behind LLM benchmark scores

25 reproducible audits of the metrics and gold labels behind LLM benchmark scores

Comments
4 min read
How Query, Key, and Value (QKV) Work in Transformers

How Query, Key, and Value (QKV) Work in Transformers

Comments 1
5 min read
My Japanese Tutor Agent Works — Except Its Brain Calls Everything a Particle

My Japanese Tutor Agent Works — Except Its Brain Calls Everything a Particle

Comments
3 min read
Day 38: GPT-1 to GPT-3: The Evolution of Scale

Day 38: GPT-1 to GPT-3: The Evolution of Scale

Comments
5 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.