lixiangnlp Goto Github PK

nnsmt

Statistical machine translation system based on pure neural joint probability model.

node-unfluff

Automatically extract body content (and other cool stuff) from an html document

nolearn

Abstractions around neural net libraries, most notably Lasagne.

nplm

Fork of http://nlg.isi.edu/software/nplm/ for threadsafety and efficiency.

ntm-tensorflow

Neural Turing Machine in Tensorflow

nytimes-corpus-extractor

Extract all the fields from the NY Times Corpus to a csv

opencc

A project for conversion between Traditional and Simplified Chinese

openerdns

OpenerDNS: 是面向**用户开放的"高速 安全 免费"的域名解析服务器。

openwrt-gfw

Openwrt的翻墙解决方案

oxlm

OxLM: Oxford Neural Language Modelling Toolkit

papernotes

parex

Parex paraphrase extractor

pattern

Web mining module for Python, with tools for scraping, natural language processing, machine learning, network analysis and visualization.

penn-parser-cyk-viterbi

Treebank Parser, CYK, and Viterbi

pkusumsum

First publish for PKUSUMSUM

platoon

Multi-GPU mini-framework for Theano

pragmatic_segmenter

Pragmatic Segmenter is a rule-based sentence boundary detection gem that works out-of-the-box across many languages.

probingpt

ProbingPT, a phrase table for Moses the statistical machine translation decoder.

punctuator2

A bidirectional recurrent neural network model with attention mechanism for restoring missing punctuation in unsegmented text

pynlpir

A Python wrapper around the NLPIR/ICTCLAS Chinese segmentation software.

pyrouge

An interface to and, in time, a Python reimplementation of the ROUGE package for evaluating summarization

pysrilm

An extremely simple Python wrapper for the SRI Language Modeling toolkit

python-fizzle

Damerau–Levenshtein distance (fuzzy string matching) for python with support of unicode and custom edit costs

python-goose

Html Content / Article Extractor, web scrapping lib in Python

pyxdameraulevenshtein

pyxDamerauLevenshtein implements the Damerau-Levenshtein (DL) edit distance algorithm for Python in Cython for high performance.

qe-clean

Parallel data cleaning inspired by quality estimation

qualitative

Software of Quality Estimation for Machine Translation ouput using machine learning trained on human selections

rake

A python implementation of the Rapid Automatic Keyword Extraction

rake-1

Key phrase extraction algorithm

rc-data

Question answering dataset featured in "Teaching Machines to Read and Comprehend