Natural Language Processing - DEV Community

Skip to content

DEV Community

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

Nov 10

Clustering the news with cheap models: a measured look at embeddings, online centroids and entity extraction

#machinelearning #nlp #postgres #datascience

14 min read

Nov 10

I built bhasha-kit: a free offline Python library for Hindi & Bengali text

#showdev #python #opensource #nlp

1 min read

Shenao Yu

Nov 10

Is semantic chunking actually better than rule-based splitting for RAG retrieval?

#rag #nlp #machinelearning #programming

5 min read

Quantooox

Nov 9

We scored every headline with FinBERT. News tone didn't predict the next month.

#nlp #machinelearning #datascience #python

2 min read

Tasnem Islam Prome

Nov 9

I Built TicketTriage AI: An NLP-Based Support Ticket Classification System

#ai #machinelearning #nlp #python

1 min read

Hanako H.

Nov 9

How to label text with a local LLM so it only answers with your labels

#llm #python #nlp #machinelearning

5 min read

Nov 8

Your Daily Mortgage Import Can Leak History Into Evaluation

#python #rag #machinelearning #nlp

8 min read

Nov 8

NLP #2: Unicode and UTF-8

#nlp #machinelearning #tokenization #unicode

13 min read

Nov 7

Your Salary Corpus Is Counting Currency Views as Evidence

#python #rag #machinelearning #nlp

6 min read

MV2 (Munim, Inc.)

Nov 7

When strong models agree on a different GSM8K answer, the answer key is usually wrong

#machinelearning #datascience #nlp #benchmarks

3 min read

Daniel Oliveira

Nov 7

Counting words in speech-to-text earnings calls: the "Tranium" problem

#ai #mcp #nlp #finance

2 min read

MV2 (Munim, Inc.)

Nov 7

How many wrong answer keys are left in MMLU?

#machinelearning #datascience #nlp #benchmarks

3 min read

MV2 (Munim, Inc.)

Nov 6

Our best shortcut for finding wrong MMLU answer keys failed its replication

#machinelearning #datascience #nlp #benchmarks

4 min read

MV2 (Munim, Inc.)

Nov 6

How strong does a model panel need to be to find wrong MMLU answer keys?

#machinelearning #datascience #nlp #benchmarks

4 min read

Nov 6

Your RAG Corpus Should Keep Answer Cards Attributed

#python #rag #nlp #machinelearning

6 min read

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