Mind the Gap: Assessing Wiktionary's Crowd-Sourced Linguistic Knowledge on Morphological Gaps in Two Related Languages
arxiv.org·1d
🤖Automated Parsing
davidchisnall/igk: I got Knuth'd: A compiler for documents
github.com·8h
📝Concrete Syntax
Stop Words Using Spacy - NLP
dev.to·1d·
Discuss: DEV
📝Text Parsing
Linguistics vs. archeology and (physical) anthropology
languagelog.ldc.upenn.edu·14h
📡Frequency Archaeology
The more LLMs think, the worse they translate
nuenki.app·3h·
Discuss: Hacker News
⚙️Compression Benchmarking
Cactus Language • Syntax 11
inquiryintoinquiry.com·1d
📝Concrete Syntax
Kumo Surfaces Structured Data Patterns Generative AI Misses
thenewstack.io·53m
📊Graph Databases
Text2Struct: A Machine Learning Pipeline for Mining Structured Data from Text
arxiv.org·1d
🔤Character Classification
Why Your Next LLM Might Not Have A Tokenizer
towardsdatascience.com·19h
🤖Grammar Induction
Lemmatization as a Classification Task: Results from Arabic across Multiple Genres
arxiv.org·1d
🤖Grammar Induction
Computational Approaches to Understanding Large Language Model Impact on Writing and Information Ecosystems
arxiv.org·1d
📜Digital Philology
DRIFT: Data Reduction via Informative Feature Transformation- Generalization Begins Before Deep Learning starts
arxiv.org·10h
🧠Machine Learning
Accumulation of Cognitive Debt When Using an AI Assistant for Essay Writing Task
media.mit.edu·1d·
Discuss: Hacker News
🧠Intelligence Compression
Machine Learning Fundamentals: active learning
dev.to·22h·
Discuss: DEV
🤖Grammar Induction
Unveiling Factors for Enhanced POS Tagging: A Study of Low-Resource Medieval Romance Languages
arxiv.org·1d
👁️Medieval OCR
PATCH! {P}sychometrics-{A}ssis{T}ed Ben{CH}marking of Large Language Models against Human Populations: A Case Study of Proficiency in 8th Grade Mathematics
arxiv.org·10h
🧠Intelligence Compression
QuranMorph: Morphologically Annotated Quranic Corpus
arxiv.org·1d
📋Document Grammar
Multilingual Tokenization through the Lens of Indian Languages: Challenges and Insights
arxiv.org·1d
📝Text Parsing
Markov-Enhanced Clustering for Long Document Summarization: Tackling the 'Lost in the Middle' Challenge with Large Language Models
arxiv.org·1d
📄Text Chunking
The Internal Inconsistency of Large Language Models
blog.kortlepel.com·22h·
Discuss: Hacker News
💻Local LLMs