| 1 |
Modeling the effect of military oxygen masks on speech characteristics
|
|
|
|
In: Interspeech 2021 ; https://hal.archives-ouvertes.fr/hal-03325087 ; Interspeech 2021, Aug 2021, Brno, Czech Republic (2021)
|
|
BASE
|
|
Show details
|
|
|
| 2 |
Simulating reading mistakes for child speech Transformer-based phone recognition
|
|
|
|
In: Annual Conference of the International Speech Communication Association (INTERSPEECH) ; https://hal.archives-ouvertes.fr/hal-03257870 ; Annual Conference of the International Speech Communication Association (INTERSPEECH), Aug 2021, Brno, Czech Republic (2021)
|
|
BASE
|
|
Show details
|
|
|
| 3 |
A Data Augmentation Approach for Sign-Language-To-Text Translation In-The-Wild ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 4 |
Effekten av textaugmenteringsstrategier på träffsäkerhet, F1-värde och viktat F1-värde ; The effect of text data augmentation strategies on Accuracy, F1-score, and weighted F1-score
|
|
|
|
BASE
|
|
Show details
|
|
|
| 5 |
Using Data Augmentation and Time-Scale Modification to Improve ASR of Children’s Speech in Noisy Environments
|
|
|
|
In: Applied Sciences ; Volume 11 ; Issue 18 (2021)
|
|
BASE
|
|
Show details
|
|
|
| 6 |
Generating Synthetic Disguised Faces with Cycle-Consistency Loss and an Automated Filtering Algorithm
|
|
|
|
In: Mathematics; Volume 10; Issue 1; Pages: 4 (2021)
|
|
BASE
|
|
Show details
|
|
|
| 7 |
Volumetric changes at implant sites: A systematic appraisal of traditional methods and optical scanning- based digital technologies
|
|
|
|
BASE
|
|
Show details
|
|
|
| 8 |
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
|
|
|
|
|
