Neural Machine Translation (NMT) has seen tremendous growth in the last ten years since
the early 2000s and has already entered a mature phase. While considered the most widely …

Adult semantic memory has been traditionally conceptualized as a relatively static memory
system that consists of knowledge about the world, concepts, and symbols. Considerable …

We evaluate the reasoning abilities of large language models in multilingual settings. We
introduce the Multilingual Grade School Math (MGSM) benchmark, by manually translating …

We present modality gap, an intriguing geometric phenomenon of the representation space
of multi-modal models. Specifically, we show that different data modalities (eg images and …

Informally, the'linear representation hypothesis' is the idea that high-level concepts are
represented linearly as directions in some representation space. In this paper, we address …

This paper demonstrates that multilingual denoising pre-training produces significant
performance gains across a wide variety of machine translation (MT) tasks. We present …

Multilingual BERT (mBERT) trained on 104 languages has shown surprisingly good cross-
lingual performance on several NLP tasks, even without explicit cross-lingual signals …

A transcompiler, also known as source-to-source translator, is a system that converts source
code from a high-level programming language (such as C++ or Python) to another …

Similarity search finds application in database systems handling complex data such as
images or videos, which are typically represented by high-dimensional features and require …

The goal of few-shot learning (FSL) is to recognize a set of novel classes with only few
labeled samples by exploiting a large set of abundant base class samples. Adopting a meta …