cp-lim Goto Github PK

acl2019-odee

This is the code for our ACL 2019 paper "Open Domain Event Extraction Using Neural Latent Variable Models"

article-code

burst_detection

Detect bursts in batched data using Kleinberg's (2002) algorithm.

comfyui-llm

courses

Course materials for the Data Science Specialization: https://www.coursera.org/specialization/jhudatascience/1

docker-spark-cluster

A simple spark standalone cluster for your testing environment purposses

embeddings

Fast, DB Backed pretrained word embeddings for natural language processing.

end2end_neural_el

es-dedupe

Tool for removing duplicate documents from Elasticsearch

evolutionary-computation

fuzzy-art-neural-network

Implement Fuzzy ART in python

gan-tutorial

gdeltpyr

Python based framework to retreive Global Database of Events, Language, and Tone (GDELT) version 1.0 and version 2.0 data.

information-extraction-chinese

Chinese Named Entity Recognition with IDCNN/biLSTM+CRF, and Relation Extraction with biGRU+2ATT 中文实体识别与关系提取

janome

Japanese morphological analysis engine written in pure Python

laser

Language-Agnostic SEntence Representations

lime

Lime: Explaining the predictions of any machine learning classifier

mecab-python3

:snake: mecab-python. you can find original version here:http://taku910.github.io/mecab/

microblog

flask_Tutorial

namaco

Character Based Named Entity Recognition.

ncel

news-graph

Key information extraction from text and graph visualization

oseti

Dictionary based Sentiment Analysis for Japanese

pybursts

A Python port of the R implementation of Kleinberg's burst detection algorithm

pytorch_geometric

Geometric Deep Learning Extension Library for PyTorch

pytorchic-bert

Pytorch Implementation of Google BERT

rivet

The open-source visual AI programming environment and TypeScript library

rrwel

Neural Collective Entity Linking Based on Recurrent Random Walk Network Learning. Code from IJCAI 2019 paper.

sengiri

Yet another sentence-level tokenizer for the Japanese text

snorkel

A system for quickly generating training data with weak supervision