1 |
The effect of domain and diacritics in Yorùbá-English neural machine translation
|
|
Adelani, David,; Ruiter, Dana; Alabi, Jesujoba,; Adebonojo, Damilola; Ayeni, Adesina; Adeyemi, Mofetoluwa; Awokoya, Ayodele; Espana-Bonet, Cristina
|
|
In: 18th Biennial Machine Translation Summit ; https://hal.inria.fr/hal-03350967 ; 18th Biennial Machine Translation Summit, Aug 2021, Orlando, United States (2021)
|
|
Abstract:
International audience ; Massively multilingual machine translation (MT) has shown impressive capabilities, including zero and few-shot translation between low-resource language pairs. However, these models are often evaluated on high-resource languages with the assumption that they generalize to low-resource ones. The difficulty of evaluating MT models on low-resource pairs is often due to lack of standardized evaluation datasets. In this paper, we present MENYO-20k, the first multi-domain parallel corpus with a special focus on clean orthography for Yorùbá-English with standardized train-test splits for benchmarking. We provide several neural MT benchmarks and compare them to the performance of popular pre-trained (massively multilingual) MT models both for the heterogeneous test set and its subdomains. Since these pre-trained models use huge amounts of data with uncertain quality, we also analyze the effect of diacritics, a major characteristic of Yorùbá, in the training data. We investigate how and when this training condition affects the final quality and intelligibility of a translation. Our models outperform massively multilingual models such as Google (+8.7 BLEU) and Facebook M2M (+9.1 BLEU) when translating to Yorùbá, setting a high quality benchmark for future research.
|
|
Keyword:
[INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]
|
|
URL: https://hal.inria.fr/hal-03350967 https://hal.inria.fr/hal-03350967/document https://hal.inria.fr/hal-03350967/file/adelani_MTSummit2021.pdf
|
|
BASE
|
|
Hide details
|
|
2 |
The Effect of Domain and Diacritics in Yorùbá-English Neural Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
EdinSaar@WMT21: North-Germanic Low-Resource Multilingual NMT ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Integrating Unsupervised Data Generation into Self-Supervised Neural Machine Translation for Low-Resource Languages ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Modeling Profanity and Hate Speech in Social Media with Semantic Subspaces ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|