ruimao1988 Goto Github PK

sumo

Suggested Upper Merged Ontology (SUMO)

superclue

SuperCLUE: 中文通用大模型综合性基准 | A Benchmark for Foundation Models in Chinese

tamr

tensor2tensor

Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.

tensorflow

Computation using data flow graphs for scalable machine learning

tensorflow-examples

TensorFlow Tutorial and Examples for Beginners with Latest APIs

text_gru_attention_classify

text_gru_classify

text classify with gru model

textract

extract text from any document. no muss. no fuss.

torchnlp

Easy to use NLP library built on PyTorch and TorchText

transformer

A TensorFlow Implementation of the Transformer: Attention Is All You Need

transformer-xl

treelstm

Tree-structured Long Short-Term Memory networks (http://arxiv.org/abs/1503.00075)

urban-dictionary-entry-collector

Script used to collect entry data from Urban Dictionary

usc_projects

Graduate School Projects

wacky

A set of programs for running NLP models against the ukWaC corpus

wikiextractor

A tool for extracting plain text from Wikipedia dumps

wizmap

Explore and interpret large embeddings in your browser with interactive visualization! 📍

word-sense-disambiguation

Word Sense Disambiguation using Word Specific models, All word models and Hierarchical models

word2vec

Python interface to Google word2vec

word2vec-1

This tool provides an efficient implementation of the continuous bag-of-words and skip-gram architectures for computing vector representations of words. These representations can be subsequently used in many natural language processing applications and for further research.

word2vec-api

Simple web service providing a word embedding model

word2vecpy

Python implementation of CBOW and skip-gram word vector models, and hierarchical softmax and negative sampling learning algorithms

word_forms

Accurately generate all possible forms of an English word e.g "election" --> "elect", "electoral", "electorate" etc.

wp2txt

WP2TXT extracts plain text data from Wikipedia dump file (encoded in XML/compressed with Bzip2) stripping all the MediaWiki markups and other metadata.

zeno-build

Build, evaluate, analyze, and understand LLM-based apps