| 1 |
Rethinking Data Augmentation for Low-Resource Neural Machine Translation: A Multi-Task Learning Approach
|
|
|
|
Abstract:
In the context of neural machine translation, data augmentation (DA) techniques may be used for generating additional training samples when the available parallel data are scarce. Many DA approaches aim at expanding the support of the empirical data distribution by generating new sentence pairs that contain infrequent words, thus making it closer to the true data distribution of parallel sentences. In this paper, we propose to follow a completely different approach and present a multi-task DA approach in which we generate new sentence pairs with transformations, such as reversing the order of the target sentence, which produce unfluent target sentences. During training, these augmented sentences are used as auxiliary tasks in a multi-task framework with the aim of providing new contexts where the target prefix is not informative enough to predict the next word. This strengthens the encoder and forces the decoder to pay more attention to the source representations of the encoder. Experiments carried out on six low-resource translation tasks show consistent improvements over the baseline and over DA methods aiming at extending the support of the empirical data distribution. The systems trained with our approach rely more on the source tokens, are more robust against domain shift and suffer less hallucinations. ; Work funded by the European Union’s Horizon 2020 research and innovation programme under grant agreement number 825299, project Global Under-Resourced Media Translation (GoURMET); and by Generalitat Valenciana through project GV/2021/064. The computational resources used for the experiments were funded by the European Regional Development Fund through project IDIFEDER/2020/003.
|
|
Keyword:
Data augmentation; Lenguajes y Sistemas Informáticos; Multi-task learning approach; Neural machine translation
|
|
URL: https://doi.org/10.18653/v1/2021.emnlp-main.669
http://hdl.handle.net/10045/121939
|
|
BASE
|
|
Hide details
|
|
|
| 2 |
Understanding the effects of word-level linguistic annotations in under-resourced neural machine translation
|
|
|
|
BASE
|
|
Show details
|
|
|
| 3 |
The Universitat d'Alacant submissions to the English-to-Kazakh news translation task at WMT 2019 ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 4 |
The Universitat d'Alacant submissions to the English-to-Kazakh news translation task at WMT 2019 ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 5 |
Quantitative Fine-Grained Human Evaluation of Machine Translation Systems: a Case Study on English to Croatian ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 6 |
Fine-grained human evaluation of neural versus phrase-based machine translation ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 7 |
A Multifaceted Evaluation of Neural versus Phrase-Based Machine Translation for 9 Language Directions ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 8 |
Assisting non-expert speakers of under-resourced languages in assigning stems and inflectional paradigms to new word entries of morphological dictionaries
|
|
|
|
BASE
|
|
Show details
|
|
|
| 9 |
Fine-Grained Human Evaluation of Neural Versus Phrase-Based Machine Translation
|
|
|
|
In: Prague Bulletin of Mathematical Linguistics , Vol 108, Iss 1, Pp 121-132 (2017) (2017)
|
|
BASE
|
|
Show details
|
|
|
| 10 |
Integrating Rules and Dictionaries from Shallow-Transfer Machine Translation into Phrase-Based Statistical Machine Translation
|
|
|
|
BASE
|
|
Show details
|
|
|
| 11 |
RuLearn: an Open-source Toolkit for the Automatic Inference of Shallow-transfer Rules for Machine Translation
|
|
|
|
BASE
|
|
Show details
|
|
|
| 12 |
RuLearn: an Open-source Toolkit for the Automatic Inference of Shallow-transfer Rules for Machine Translation
|
|
|
|
In: Prague Bulletin of Mathematical Linguistics , Vol 106, Iss 1, Pp 193-204 (2016) (2016)
|
|
BASE
|
|
Show details
|
|
|
| 13 |
A generalised alignment template formalism and its application to the inference of shallow-transfer machine translation rules from scarce bilingual corpora
|
|
|
|
BASE
|
|
Show details
|
|
|
| 14 |
An open-source toolkit for integrating shallow-transfer rules into phrase-based statistical machine translation
|
|
|
|
BASE
|
|
Show details
|
|
|
| 15 |
Choosing the correct paradigm for unknown words in rule-based machine translation systems
|
|
|
|
BASE
|
|
Show details
|
|
|
| 16 |
The Universitat d’Alacant hybrid machine translation system for WMT 2011
|
|
|
|
BASE
|
|
Show details
|
|
|
| 17 |
Integrating shallow-transfer rules into phrase-based statistical machine translation
|
|
|
|
BASE
|
|
Show details
|
|
|
| 18 |
Enriching a statistical machine translation system trained on small parallel corpora with rule-based bilingual phrases
|
|
|
|
BASE
|
|
Show details
|
|
|
| 19 |
A Widely Used Machine Translation Service and its Migration to a Free/Open-Source Solution : the Case of Softcatalà
|
|
|
|
BASE
|
|
Show details
|
|
|
| 20 |
ScaleMT: a free/open-source framework for building scalable machine translation web services
|
|
|
|
BASE
|
|
Show details
|
|
|
|
|
