Melvin Johnson

nmT5 -- Is parallel data still relevant for pre-training massively multilingual language models?

2021 · arXiv (Cornell University)

Recently, mT5 - a massively multilingual version of T5 - leveraged a unified text-to-text format to attain state-of-the-art results on a wide variety of multilingual NLP tasks. In this paper, we investigate the impact of …

mSLAM: Massively multilingual joint pre-training for speech and text

2022 · arXiv (Cornell University)

We present mSLAM, a multilingual Speech and LAnguage Model that learns cross-lingual cross-modal representations of speech and text by pre-training jointly on large amounts of unlabeled speech and text in multiple languages. mSLAM combines w2v-BERT …

Multilingual Document-Level Translation Enables Zero-Shot Transfer From Sentences to Documents

2021 · arXiv (Cornell University)

Document-level neural machine translation (DocNMT) achieves coherent translations by incorporating cross-sentence context. However, for most language pairs there's a shortage of parallel documents, although parallel sentences are readily available. In this paper, we study whether …

Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation

2016 · arXiv (Cornell University)

Neural Machine Translation (NMT) is an end-to-end learning approach for automated translation, with the potential to overcome many of the weaknesses of conventional phrase-based translation systems. Unfortunately, NMT systems are known to be computationally expensive …

Google’s Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation

2017 · Transactions of the Association for Computational Linguistics

We propose a simple solution to use a single Neural Machine Translation (NMT) model to translate between multiple languages. Our solution requires no changes to the model architecture from a standard NMT system but instead …

Zero-Shot Cross-lingual Classification Using Multilingual Neural Machine Translation

2018 · arXiv (Cornell University)

Transferring representations from large supervised tasks to downstream tasks has shown promising results in AI fields such as Computer Vision and Natural Language Processing (NLP). In parallel, the recent progress in Machine Translation (MT) has …

Massively Multilingual Neural Machine Translation

2019

Roee Aharoni, Melvin Johnson, Orhan Firat. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). 2019.

The Missing Ingredient in Zero-Shot Neural Machine Translation

2019 · arXiv (Cornell University)

Multilingual Neural Machine Translation (NMT) models are capable of translating between multiple source and target languages. Despite various approaches to train such models, they have difficulty with zero-shot translation: translating between language pairs that were …

Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling

2019 · arXiv (Cornell University)

Lingvo is a Tensorflow framework offering a complete solution for collaborative deep learning research, with a particular focus towards sequence-to-sequence models. Lingvo models are composed of modular building blocks that are flexible and easily extensible, …

Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation

2016 · arXiv (Cornell University)

We propose a simple solution to use a single Neural Machine Translation (NMT) model to translate between multiple languages. Our solution requires no change in the model architecture from our base system but instead introduces …

Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges

2019 · arXiv (Cornell University)

We introduce our efforts towards building a universal neural machine translation (NMT) system capable of translating between any language pair. We set a milestone towards this goal by building a single massively multilingual NMT model …

Leveraging Weakly Supervised Data to Improve End-to-end Speech-to-text Translation

2019

End-to-end Speech Translation (ST) models have many potential advantages when compared to the cascade of Automatic Speech Recognition (ASR) and text Machine Translation (MT) models, including lowered inference latency and the avoidance of error compounding. …

Direct Speech-to-Speech Translation with a Sequence-to-Sequence Model

2019

We present an attention-based sequence-to-sequence neural network which can directly translate speech from one language into speech in another language, without relying on an intermediate text representation.The network is trained end-to-end, learning to map speech …

XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization

2020 · arXiv (Cornell University)

Much recent progress in applications of machine learning models to NLP has been driven by benchmarks that evaluate models across a wide variety of tasks. However, these broad-coverage benchmarks have been mostly limited to English, …

Gemini: A Family of Highly Capable Multimodal Models

2023 · arXiv (Cornell University)

This report introduces a new family of multimodal models, Gemini, that exhibit remarkable capabilities across image, audio, video, and text understanding. The Gemini family consists of Ultra, Pro, and Nano sizes, suitable for applications ranging …