Amjad Almahairi

The Impact of Preprocessing on Arabic-English Statistical and Neural Machine Translation

2019 · arXiv (Cornell University)

Neural networks have become the state-of-the-art approach for machine translation (MT) in many languages. While linguistically-motivated tokenization techniques were shown to have significant effects on the performance of statistical MT, it remains unclear if those …

Unsupervised Learning of Dense Visual Representations

2020 · arXiv (Cornell University)

Contrastive self-supervised learning has emerged as a promising approach to unsupervised visual representation learning. In general, these methods learn global (image-level) representations that are invariant to different views (i.e., compositions of data augmentation) of the …

Learning Easily Updated General Purpose Text Representations with Adaptable Task-Specific Prefixes

2023 · arXiv (Cornell University)

Many real-world applications require making multiple predictions from the same text. Fine-tuning a large pre-trained language model for each downstream task causes computational burdens in the inference time due to several times of forward passes. …

Llama 2: Open Foundation and Fine-Tuned Chat Models

2023 · arXiv (Cornell University)

In this work, we develop and release Llama 2, a collection of pretrained and fine-tuned large language models (LLMs) ranging in scale from 7 billion to 70 billion parameters. Our fine-tuned LLMs, called Llama 2-Chat, …