Install
Natural Language Processing
Text, speech, translation, and retrieval with modern NLP techniques.
- 18 Tracked terms
- Last 30 days Feed window
What this topic collects on
An article joins this feed when it matches these terms. Each one is also a search of its own.
Related topics
Latest in Natural Language Processing
# Beyond Transformers: A Mathematical Critique of Cross-Lingual Diffusion Architectures
2+ hour, 35+ min ago (424+ words) The current state of multilingual NLP is dominated by transformer-based architectures that often treat cross-lingual alignment as a secondary optimization task. For researchers and engineers working with low-resource languages or requiring strict semantic preservation, the "black box" nature of proprietary…...
A model doesn't read text: what a tokenizer decides for you
7+ hour, 17+ min ago (1022+ words) Originally published at cchinchilla.dev. Part 1 of From code to weights, a 12-part series on ML fundamentals for engineers. A language model has never seen a letter. It sees integers. Somewhere between your string and the first matrix multiply there's…...
I Counted the Words in My Prompt — Then Learned Why AI Doesn’t Actually Read Words
5+ hour, 39+ min ago (1041+ words) I thought AI saw the same words I saw. Then I learned about tokens. When I type something into ChatGPT, I see …...
Machine Learning Concepts: The Bigger Picture
11+ hour, 43+ min ago (27+ words) When you start learning AI, machine learning can feel confusing because there are so many new terms. Supervised learning, unsupervised learning …...
How I Built a 150 GB Multilingual & Code Dataset for Central Asian AI (And Fought Out-of-Memory Errors for 10 Hours)
1+ day, 8+ hour ago (326+ words) Hi Dev.to! While tech giants are competing to train LLMs on trillions of English tokens, there is a severe shortage of high-quality open-source datasets for Central Asian languages (Kyrgyz, Kazakh, Uzbek, Tajik). Technical corpora for these regions are scarce,…...
"machine learning"~2 — phrase and proximity search in Whoosh
1+ day, 10+ hour ago (362+ words) When users type quotes around words, they mean it. "machine learning" should not match a page that happens to contain machine in one paragraph and learning three paragraphs later. Bag-of-words scoring alone can't express that intent — you need phrase and…...
Inside the Resume Parsing Pipeline: Where Extraction Breaks
1+ day, 13+ hour ago (1010+ words) If you’re building or evaluating an ATS integration, resume parsing looks simple from the outside and gets genuinely interesting once you look at where it fails. Here’s the pipeline, stage by stage, and the specific failure mode at each step....
Your LLM Has Never Read a Word: Tokenization Explained for Developers
1+ day, 17+ hour ago (1016+ words) You type a sentence into ChatGPT and it looks like normal English. The model doesn't see it that way. In fact, it never sees words at all. Before the model processes anything, your text is converted into a sequence of…...
Applied Sciences, Vol. 16, Pages 9294: Large Language Models in the Analysis of Radar Plotting Images in Accordance with COLREGs
1+ day, 18+ hour ago (392+ words) The development of artificial intelligence (AI) opens new possibilities for the automatic interpretation of radar images in maritime navigation. Traditionally, the interpretation of radar indications requires the experience of the officer of the watch, who assesses the risk of collision…...
Linkup Research Releases SPARSEUP: A 149M-Parameter Open-Source Sparse Embedding Model
1+ day, 18+ hour ago (450+ words) Linkup research team releases SPARSEUP, an open-source learned sparse embedding model. The model runs on a 149M-parameter ModernBERT backbone and ships under Apache 2.0. Linkup team reports 56.4 average nDCG@10 on BEIR-13. It calls this the strongest public vocabulary-based sparse encoder it…...