Search Results for author:
Found 7 papers, 4 papers with code
Data Augmentation by Concatenation for Low-Resource Translation: A Mystery and a Solution
In this paper, we investigate the driving factors behind concatenation, a simple but effective data augmentation method for low-resource neural machine translation.
Quality at a Glance: An Audit of Web-Crawled Multilingual Datasets
With the success of large-scale pre-training and multilingual modeling in Natural Language Processing (NLP), recent years have seen a proliferation of large, web-mined text datasets covering hundreds of languages.
Masked Language Model Scoring
Instead, we evaluate MLMs out of the box via their pseudo-log-likelihood scores (PLLs), which are computed by masking tokens one by one.
Transformers without Tears: Improving the Normalization of Self-Attention
We evaluate three simple, normalization-centric changes to improve Transformer training.
Ranked #4 on
Machine Translation
on IWSLT2015 English-Vietnamese
Auto-Sizing the Transformer Network: Improving Speed, Efficiency, and Performance for Low-Resource Machine Translation
Neural sequence-to-sequence models, particularly the Transformer, are the state of the art in machine translation.
Improving Lexical Choice in Neural Machine Translation
We explore two solutions to the problem of mistranslating rare words in neural machine translation.
Transfer Learning across Low-Resource, Related Languages for Neural Machine Translation
We present a simple method to improve neural translation of a low-resource language pair using parallel data from a related, also low-resource, language pair.
