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.
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
Building NLP Tools for Languages That Big Tech Ignores

Building NLP Tools for Languages That Big Tech Ignores

Comments
2 min read
Український лематизатор тепер вбудовано в Manticore Search

Український лематизатор тепер вбудовано в Manticore Search

Comments
1 min read
Shipping a BERT model as a browser extension

Shipping a BERT model as a browser extension

Comments
4 min read
How I improved my fact-checker from F1 0.655 0.813 — what actually changed

How I improved my fact-checker from F1 0.655 0.813 — what actually changed

Comments
3 min read
Multi-Voice Audiobooks: The Character Attribution Problem

Multi-Voice Audiobooks: The Character Attribution Problem

Comments
2 min read
Making Two TTS Voices Sound Like an Actual Conversation

Making Two TTS Voices Sound Like an Actual Conversation

Comments
2 min read
Why Japanese and Korean Break Your Text Processing Pipeline

Why Japanese and Korean Break Your Text Processing Pipeline

2
Comments
2 min read
minbpe vs turboBPE: Two ways to think about tokenizer training

minbpe vs turboBPE: Two ways to think about tokenizer training

Comments
4 min read
Replacing Cross-Encoder Reranking with a Weighted Hybrid Score

Replacing Cross-Encoder Reranking with a Weighted Hybrid Score

Comments
5 min read
Four ways to split sentences (without machine learning)

Four ways to split sentences (without machine learning)

1
Comments
6 min read
Part 2: Why We Built Our Own TinyBERT (and How It Beat Shiprocket's) - Indian Address Parser

Part 2: Why We Built Our Own TinyBERT (and How It Beat Shiprocket's) - Indian Address Parser

1
Comments
7 min read
When translation gives you one answer and no context

When translation gives you one answer and no context

Comments
2 min read
Moroccan Darija in NLP: Challenges and Opportunities

Moroccan Darija in NLP: Challenges and Opportunities

3
Comments
5 min read
I Built an Open-Source Dataset of 985 Dream Symbols — Here's How You Can Use It

I Built an Open-Source Dataset of 985 Dream Symbols — Here's How You Can Use It

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