Name: Joachim Wagner
Type: User
Company: Dublin City University
Bio: Natural language processing researcher with interest in high-performance computing, machine learning and storage systems. Programming since 1983.
Location: Dublin, Ireland
Blog: https://www.computing.dcu.ie/~jwagner/
Joachim Wagner's Projects
Evaluate rationales in the task of aspect-based sentiment analysis against manually annoated sentiment expressions
Data and software for building the ACL Anthology.
Development of userspace BTRFS tools
CoNLL 2018 UD Shared Task
Pre-trained ELMo Representations for Many Languages
F3 - Fight Flash Fraud
Simple, fast unsupervised word aligner
Fast Neural Machine Translation in C++
Moses, the machine translation system
Backup of gogs mtb-tri-training repo
Repository for paper submission to DeepLo Workshop 2019.
Flexible and powerful data analysis / manipulation library for Python, providing labeled data structures similar to R data.frame objects, statistical functions, and much more
Partclone provides utilities to backup a partition smartly and it is designed for higher compatibility of the file system by using existing library.
An Advanced tool to Crack Any Password Protected PDF file. A very user friendly script especially for noob hackers.
Unsupervised Word Segmentation for Neural Machine Translation and Text Generation
Treebank embedding vector prediction for out-of-domain dependency parsing
Linear combination of UD basic parse trees for parser ensembles
English data
A single model that parses Universal Dependencies across all (75) languages.
CoNLL 2018 Shared Task Team UDPipe-Future
A transition-based parser for Universal Dependencies with BiLSTM word and character representations.
Universal segmenter based on the Universal Dependency framework, written by Y. Shao, Uppsala University
PyTorch original implementation of Cross-lingual Language Model Pretraining.