surafelml/Afro-NMT

LOW-RESOURCE NEURAL MACHINE TRANSLATION: A BENCHMARK FOR FIVE AFRICAN LANGUAGES # Low Resource Neural Machine Ttranslation: A Benchmark For Five African Languages --- This repo provides data and experimental details for the paper LOW-RESOURCE NEURAL MACHINE TRANSLATION: A BENCHMARK FOR FIVE AFRICAN LANGUAGES . Updates: - [July 2020] Data and scripts are available (see ./data, ./scripts directories) - [March, 2020] Data, scripts, pre-trained models will be available asap. ## Paper Summary / Approaches --- *...benchmark NMT between English and five African LRL pairs (Swahili, Amharic, Tigrigna, Oromo, Somali [SATOS]). We collected the available resources on the SATOS languages to evaluate the current state of NMT for LRLs. Our evaluation, comparing a baseline single language pair __supervised NMT__ model against __semi-supervised__ learning, __transfer-learning__, and __multilingual modeling__, shows significant performance improvements both in the En → LRL and LRL → En directions.* Baseline Supervised NMT - Benchmarks a single language pair NMT models between En and the SATOS languages. Semi-Supervised NMT - Utilizes back-translation that leverages monolingual data to improve the supervised models. Transfer-Learning NMT - Utilizes dynamic transfer-learning approach from a parent multilingual model to initialize single language pair child models. Multilingual NMT - Trains a multilingual model ( of 10 directions) aggregating data from all the pairs. *Additional summaries on each of these approaches can be found in the paper. Further readings on semi-supervised, transfer-learning, and multilingual-nmt* ## Data and Experimental Setup --- ### Requirements - NMT Library OpenNMT-tf - Mosesdecoder - SentenciePiece - WikiExtractor - Opus Corpus Tools For installing requirements and initial setup, run: `./env-setup.sh` ## Data Preparation - Monolingual Data (wikipedia articles) `./scripts/get-monolingual-data.sh [lang-id]` - Parallel Data (Opus data of differen corpus) `./scripts/get-opus-data.sh [src-lang-id] [tgt-lan …