Marcello Federico
8 papers in the PaperMetrix corpus
Papers by this author
-
Compositional Representation of Morphologically-Rich Input for Neural Machine Translation
2018
Neural machine translation (NMT) models are typically trained with fixed-size input and output vocabularies, which creates an important bottleneck on their accuracy and generalization capability. As a solution, various studies proposed segmenting words into sub-word …
-
Transfer Learning in Multilingual Neural Machine Translation with Dynamic Vocabulary
2018 · arXiv (Cornell University)
We propose a method to transfer knowledge across neural machine translation (NMT) models by means of a shared dynamic vocabulary. Our approach allows to extend an initial model for a given language pair to cover …
-
TICO-19: the Translation Initiative for COvid-19
2020
Antonios Anastasopoulos, Alessandro Cattelan, Zi-Yi Dou, Marcello Federico, Christian Federmann, Dmitriy Genzel, Franscisco Guzmán, Junjie Hu, Macduff Hughes, Philipp Koehn, Rosie Lazar, Will Lewis, Graham Neubig, Mengmeng Niu, Alp Öktem, Eric Paquin, Grace Tang, Sylwia …
-
End-to-End Single-Channel Speaker-Turn Aware Conversational Speech Translation
2023 · arXiv (Cornell University)
Conventional speech-to-text translation (ST) systems are trained on single-speaker utterances, and they may not generalize to real-life scenarios where the audio contains conversations by multiple speakers. In this paper, we tackle single-channel multi-speaker conversational ST …
-
A Shocking Amount of the Web is Machine Translated: Insights from Multi-Way Parallelism
2024 · arXiv (Cornell University)
We show that content on the web is often translated into many languages, and the low quality of these multi-way translations indicates they were likely created using Machine Translation (MT). Multi-way parallel, machine generated content …
-
Multi-Domain Neural Machine Translation through Unsupervised Adaptation
2017
We investigate the application of Neural Machine Translation (NMT) under the following three conditions posed by realworld application scenarios. First, we operate with an input stream of sentences coming from many different domains and with …
-
The IWSLT 2015 Evaluation Campaign
2015 · Repository KITopen (Karlsruhe Institute of Technology)
The IWSLT 2016 Evaluation Campaign featured two tasks: the translation of talks and the translation of video conference conversations. While the first task extends previously offered tasks with talks from a different source, the second …
-
The IWSLT 2019 Evaluation Campaign
2019 · Research Publications (Maastricht University)
The IWSLT 2019 evaluation campaign featured three tasks: speech translation of (i) TED talks and (ii) How2 instructional videos from English into German and Portuguese, and (iii) text translation of TED talks from English into …