Marzieh Fadaee's repositories
DataAugmentationNMT
Data Augmentation for Neural Machine Translation
IdiomTranslationDS
De-En and En-De idiom translation test sets
TS_Embeddings
Learning topic-sensitive word embeddings
variation-generation
Generate sentence variations to evaluate volatility of seq2seq models
arxiv-sanity-preserver
Web interface for browsing, search and filtering recent arxiv submissions
fast_align
Simple, fast unsupervised word aligner
MSMARCO-Passage-Ranking
MS MARCO(Microsoft Machine Reading Comprehension) is a large scale dataset focused on machine reading comprehension, question answering, and passage ranking. A variant of this task will be the part of TREC and AFIRM 2019. For Updates about TREC 2019 please follow This Repository Passage Reranking task Task Given a query q and a the 1000 most relevant passages P = p1, p2, p3,... p1000, as retrieved by BM25 a succeful system is expected to rerank the most relevant passage as high as possible. For this task not all 1000 relevant items have a human labeled relevant passage. Evaluation will be done using MRR
OpenNMT-py
Open-Source Neural Machine Translation in PyTorch http://opennmt.net/
sentence-transformers
Sentence Embeddings with BERT & XLNet