RubickH

jieba

结巴中文分词

Chinese-Names-Corpus

中文人名语料库。人名生成器。中文姓名,姓氏,名字,称呼,日本人名,翻译人名,英文人名。可用于中文分词、人名实体识别。

wikiextractor

A tool for extracting plain text from Wikipedia dumps

line_profiler

Line-by-line profiling for Python

biobert

Bioinformatics'2020: BioBERT: a pre-trained biomedical language representation model for biomedical text mining

scispacy

A full spaCy pipeline and models for scientific/biomedical documents.

marian

Fast Neural Machine Translation in C++

open-images-dataset

Open Images is a dataset of ~9 million images that have been annotated with image-level labels and bounding boxes spanning thousands of classes.

Tatoeba-Challenge

fast_align

Simple, fast unsupervised word aligner

bluebert

BlueBERT, pre-trained on PubMed abstracts and clinical notes (MIMIC-III).

ChineseBLUE

Chinese Biomedical Language Understanding Evaluation benchmark (ChineseBLUE)

awesome-align

A neural word aligner based on multilingual BERT

bottom-up-attention.pytorch

A PyTorch reimplementation of bottom-up-attention models

py-bottom-up-attention

PyTorch bottom-up attention with Detectron2

bert-vocab-builder

Builds wordpiece(subword) vocabulary compatible for Google Research's BERT

RL4NMT

Reinforcement Learning for Neural Machine Translation

image-paragraph-captioning

[EMNLP 2018] Training for Diversity in Image Paragraph Captioning

RMN

IJCAI2020: Learning to Discretely Compose Reasoning Module Networks for Video Captioning

wikipedia-parallel-titles

Tools for extracting parallel corpora from article titles across languages in Wikipedia

Grounded-Image-Captioning

ParaMed

Chinese to English medical translation

WMT2020_BioMedical

fairseq_mix

Code for ICML2020 "Sequence Generation with Mixed Representations"

image-paragraph-captioning

PyTorch implementation of 'Text Embedding Bank Module for Detailed Image Paragraph Captioning'

TRANSLIT

Object-Relation-Attention-for-im2p

Ngram_LG

My modification for the research project based on GPT2.

zenme-whatsthatcalled

[experiment] Translate brand names between english and chinese using wikipedia written with svelte

cnm