Findings of the 2019 conference on machine translation (WMT19)
This paper presents the results of the premier shared task organized alongside the
Conference on Machine Translation (WMT) 2019. Participants were asked to build machine …
Conference on Machine Translation (WMT) 2019. Participants were asked to build machine …
Survey of low-resource machine translation
We present a survey covering the state of the art in low-resource machine translation (MT)
research. There are currently around 7,000 languages spoken in the world and almost all …
research. There are currently around 7,000 languages spoken in the world and almost all …
Very deep transformers for neural machine translation
We explore the application of very deep Transformer models for Neural Machine Translation
(NMT). Using a simple yet effective initialization technique that stabilizes training, we show …
(NMT). Using a simple yet effective initialization technique that stabilizes training, we show …
Tohoku-AIP-NTT at WMT 2020 news translation task
In this paper, we describe the submission of Tohoku-AIP-NTT to the WMT'20 news
translation task. We participated in this task in two language pairs and four language …
translation task. We participated in this task in two language pairs and four language …
An extensive exploration of back-translation in 60 languages
Back-translation is a data augmentation technique that has been shown to improve model
quality through the creation of synthetic training bitext. Early studies showed the promise of …
quality through the creation of synthetic training bitext. Early studies showed the promise of …
To Diverge or Not to Diverge: A Morphosyntactic Perspective on Machine Translation vs Human Translation
We conduct a large-scale fine-grained comparative analysis of machine translations (MTs)
against human translations (HTs) through the lens of morphosyntactic divergence. Across …
against human translations (HTs) through the lens of morphosyntactic divergence. Across …
Multi-hypothesis machine translation evaluation
M Fomicheva, L Specia… - Proceedings of the 58th …, 2020 - eprints.whiterose.ac.uk
Reliably evaluating Machine Translation (MT) through automated metrics is a long-standing
problem. One of the main challenges is the fact that multiple outputs can be equally valid …
problem. One of the main challenges is the fact that multiple outputs can be equally valid …
Neural machine translation: A survey of methods used for low resource languages
Machine translation (MT) is a maj or natural language processing subfield that is designed
to automatically translate human spoken languages. Neural machine translation (NMT) has …
to automatically translate human spoken languages. Neural machine translation (NMT) has …
Few-shot learning through contextual data augmentation
Machine translation (MT) models used in industries with constantly changing topics, such as
translation or news agencies, need to adapt to new data to maintain their performance over …
translation or news agencies, need to adapt to new data to maintain their performance over …
Hintedbt: Augmenting back-translation with quality and transliteration hints
Back-translation (BT) of target monolingual corpora is a widely used data augmentation
strategy for neural machine translation (NMT), especially for low-resource language pairs …
strategy for neural machine translation (NMT), especially for low-resource language pairs …