A toolkit for the creation of parallel corpora from literary texts.

Meta-Analysis with R Workshop

Code and data for the EMNLP 2020 paper: "Detecting Fine-Grained Cross-Lingual Semantic Divergences without Supervision by Learning to Rank"

A Supervised Word Alignment Method based on Cross-Language Span Prediction using Multilingual BERT

Scripts used in the analysis of dubbing corpora for Speech translation for dubbing

Tracking the progress in end-to-end speech translation

Natural Language Processing Tutorial for Deep Learning Researchers

Subtitle Splitter is an end-end application for Splitting the Bulk text into meaningful chucks for greater readability.

Returns latest research results by crawling arxiv papers and summarizing abstracts. Helps you stay afloat with so many new papers everyday.

Python port of Moses tokenizer, truecaser and normalizer

A large parallel corpus of English and Japanese

Easy-to-use word-to-word translations for 3,564 language pairs.

A collection of AWESOME things about domian adaptation

Efficient Markov Chain word alignment

Cynical data selection

Language modeling scripts based on TensorFlow

Neat (Neural Attention) Vision, is a visualization tool for the attention mechanisms of deep-learning models for Natural Language Processing (NLP) tasks. (framework-agnostic)

Visualization for simple attention and Google's multi-head attention.

Summaries and notes on Deep Learning research papers