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.
Day 13: GloVe: Global Vectors for Word Representation

Day 13: GloVe: Global Vectors for Word Representation

Comments
6 min read
Where NLP Meets Recommendations

Where NLP Meets Recommendations

Comments
5 min read
Part of Speech Tagging: How NLP Understands Grammar

Part of Speech Tagging: How NLP Understands Grammar

Comments
8 min read
🧠 I Trained a Massive Word2Vec Model on 13 Billion Russian Fiction Words — Here’s What Happened

🧠 I Trained a Massive Word2Vec Model on 13 Billion Russian Fiction Words — Here’s What Happened

Comments
4 min read
Day 12: Word2Vec Explained: Skip-Gram and CBOW

Day 12: Word2Vec Explained: Skip-Gram and CBOW

Comments
5 min read
Sentiment Analysis of Apple Tweets: An NLP Approach

Sentiment Analysis of Apple Tweets: An NLP Approach

Comments 1
2 min read
Was TinyStories the Domain or the Vocabulary?

Was TinyStories the Domain or the Vocabulary?

1
Comments 2
4 min read
Day 15: Visualizing Embeddings with t-SNE and PCA

Day 15: Visualizing Embeddings with t-SNE and PCA

1
Comments 1
5 min read
GraphProof-QA: Teaching a Small Model to Prove Its Answers

GraphProof-QA: Teaching a Small Model to Prove Its Answers

1
Comments 2
4 min read
Seu classificador de intenções é 12% pior em português: um benchmark de Laya, Strands Decider e embeddings Qwen3

Seu classificador de intenções é 12% pior em português: um benchmark de Laya, Strands Decider e embeddings Qwen3

2
Comments 5
6 min read
Tokenization in NLP: How Machines Break Down Text

Tokenization in NLP: How Machines Break Down Text

Comments
8 min read
Best Open-Weight Embedding Models for Legal Document Search

Best Open-Weight Embedding Models for Legal Document Search

10
Comments
13 min read
Bisakah Model 64 Juta Parameter Belajar Bernalar? - Membangun Model Bahasa 64M Parameter dari Nol

Bisakah Model 64 Juta Parameter Belajar Bernalar? - Membangun Model Bahasa 64M Parameter dari Nol

Comments
10 min read
Day 11: Why One-Hot Encoding Fails: The Case for Embeddings

Day 11: Why One-Hot Encoding Fails: The Case for Embeddings

1
Comments
3 min read
Day 10: Evaluation Metrics for NLP: Precision, Recall, F1, Confusion Matrix

Day 10: Evaluation Metrics for NLP: Precision, Recall, F1, Confusion Matrix

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