Cong Duy Vu Hoang

VNTC. A Large-scale Vietnamese News Text Classification Corpus

Transformer-DyNet. An Implementation of Transformer (Attention Is All You Need) in DyNet

Mantidae. A C++ Lightweight Neural Machine Translation Toolkit

TEDTalksCrawler. A Crawler for TED Talks data

OntoNotes-5.0-NER-BIO. A BIO formatted Named Entity Recognition data set extracted from the OntoNotes 5.0 release.

news-corpus. Corpus tiếng việt

tensor2tensor. A library for generalized sequence to sequence models

RelatedWorkSummarizationDataset. Dataset for the paper: Cong Duy Vu Hoang and Min-Yen Kan (2010) Towards Automated Related Work Summarization. In Proceedings of the 23rd International Conference on Computational Linguistics (COLING 2010), Beijing, China. pp. 427-435.

rasa_nlu. turn natural language into structured data

XenC. XenC: open-source data selection tool for NLP

duorat. Python

bert-as-service. Mapping a variable-length sentence to a fixed-length vector using BERT model

RIE. Scripts for crawling the plenary sessions from Europarl website (http://www.europarl.europa.eu/)

JSALT17-NMT-Lab. Repository for JSAL'17 NMT Lab

duyvuleo.github.io. Cong Duy Vu Hoang's Personal Homepage

dynet. DyNet: The Dynamic Neural Network Toolkit

ws17mt. Webpage for JSALT 2017 MT Team

scientific-paper-summarisation. Machine learning models to automatically summarise scientific papers

nlp_tasks. Natural Language Processing Tasks and References

rasa_core. machine learning based dialogue engine for AI assistants

nmt-list. A list of Neural MT implementations