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
|
|
5 |
A Data Augmentation Approach for Sign-Language-To-Text Translation In-The-Wild ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
The Effect of Domain and Diacritics in Yorùbá-English Neural Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Integrating Unsupervised Data Generation into Self-Supervised Neural Machine Translation for Low-Resource Languages ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Comparing Feature-Engineering and Feature-Learning Approaches for Multilingual Translationese Classification ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Comparing Feature-Engineering and Feature-Learning Approaches for Multilingual Translationese Classification ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Automatic classification of human translation and machine translation : a study from the perspective of lexical diversity
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Tailoring and Evaluating the Wikipedia for in-Domain Comparable Corpora Extraction ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Multilingual and Interlingual Semantic Representations for Natural Language Processing: A Brief Introduction
|
|
|
|
In: Computational Linguistics, Vol 46, Iss 2, Pp 249-255 (2020) (2020)
|
|
BASE
|
|
Show details
|
|
18 |
GeBioToolkit: Automatic Extraction of Gender-Balanced Multilingual Corpus of Wikipedia Biographies ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Massive vs. Curated Word Embeddings for Low-Resourced Languages. The Case of Yorùbá and Twi ...
|
|
|
|
BASE
|
|
Show details
|
|
20 |
Query Translation for Cross-lingual Search in the Academic Search Engine PubPsych ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|