hour Goto Github PK

a-universal-phrase-tagset

This project is mainly to establish a universal phrasal tagset for multilingual treebanks, especially for constituent structure treebanks

awesome-ocr

Links to awesome OCR projects

char-nmt-two-step-decoder

Character-level NMT with two-step decoding.

charnmt-noise

Scripts and noise data for Belinkov & Bisk 2018

cipherdaug-nmt

Official code for the paper CipherDAug: Ciphertext based Data Augmentation for Neural Machine Translation published at ACL 2022 main conference.

corpus

dataaug4nlp

Collection of papers and resources for data augmentation for NLP.

decca

DECCA: Detection of Errors and Correction in Corpus Annotation

fairseq-cipherdaug

A fairseq fork with breaking changes for CipherDAug nmt.

flores

Facebook Low Resource (FLoRes) MT Benchmark

fontfeatures

Python library for manipulating OpenType font features

google-translate-api

A simple api for google translate

hour.github.io

idn-treebank

Indonesian Treebank

jssyntaxtree

Dynamic JavaScript version of phpSyntaxTree - a tool to draw syntax trees from labelled bracket notation.

jtcc

Java library to tokenize Thai text into a list of TCCs

khmerlbdict

Khmer wordlist for line and word breaking

lang2vec

A simple library for querying the URIEL typological database.

naist-thesis-tmpl-en

A modern LaTeX template for your doctoral dissertation or master's thesis of NAIST-IS.

ncrfpp

NCRF++, a Neural Sequence Labeling Toolkit. Easy use to any sequence labeling tasks (e.g. NER, POS, Segmentation). It includes character LSTM/CNN, word LSTM/CNN and softmax/CRF components.

nmt

TensorFlow Neural Machine Translation Tutorial

nn4nlp-code

Code Samples from Neural Networks for NLP

panlex-lexicon-extractor

A library to extract bilingual lexicons from Panlex Database

python-npylm

ベイズ階層言語モデルによる教師なし形態素解析

pytorch-struct

Fast, general, and tested differentiable structured prediction in PyTorch

seanlp

Southeast Asia Natural Language Processing [Thai Vietnamese Khmer Lao Burmese(Myanmar) ]

sleukrith-set

spellcheck

Spellchecker experiment

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

typographyresearchcollection

The research collection of typography