Pinned Repositories
law-scrape-si
Sri Lankan law related pdfs scraped from http://citizenslanka.org/laws-of-sri-lanka/?lang=si converted to Sinhala text.
mbart-deploy
Deploying and monitoring an mBART model (trained for text simplification), on Kubernetes or Docker
morphdb-si
Morpological variants of Sinhala words. Extracted from FastText 300 si
muss
Code and models used in "MUSS Multilingual Unsupervised Sentence Simplification by Mining Paraphrases".
ppdb-si
Paraphrases for Sinhala words extracted using pivoting technique.
semits
Semi-Supervised Text Simplification with Back-Translation and Asymmetric Denoising Autoencoders
si-simp-scores
Readability scores for Sinhalese language
sinhala-dataset-creation
ZEST
ZEST-data
Brain Sharks's Repositories
brainsharks-fyp17/mbart-deploy
Deploying and monitoring an mBART model (trained for text simplification), on Kubernetes or Docker
brainsharks-fyp17/sinhala-dataset-creation
brainsharks-fyp17/semits
Semi-Supervised Text Simplification with Back-Translation and Asymmetric Denoising Autoencoders
brainsharks-fyp17/si-simp-scores
Readability scores for Sinhalese language
brainsharks-fyp17/cc_net
Tools to download and cleanup Common Crawl data
brainsharks-fyp17/fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
brainsharks-fyp17/law-scrape-si
Sri Lankan law related pdfs scraped from http://citizenslanka.org/laws-of-sri-lanka/?lang=si converted to Sinhala text.
brainsharks-fyp17/morphdb-si
Morpological variants of Sinhala words. Extracted from FastText 300 si
brainsharks-fyp17/muss
Code and models used in "MUSS Multilingual Unsupervised Sentence Simplification by Mining Paraphrases".
brainsharks-fyp17/ppdb-si
Paraphrases for Sinhala words extracted using pivoting technique.
brainsharks-fyp17/ZEST
brainsharks-fyp17/ZEST-data
brainsharks-fyp17/mt5-simplification
Scripts related to training and predicting Google's mt5 model
brainsharks-fyp17/Sinhala-Text-Simplification-Dataset-and-Evaluation
brainsharks-fyp17/WEIntrinsicEvaluation
W2V, skipgram and Glove models for Sinhala, along with some evaluation metrics