Efficiently Reusing Old Models Across Languages via Transfer Learning
Identifikátory výsledku
Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F20%3A10424459" target="_blank" >RIV/00216208:11320/20:10424459 - isvavai.cz</a>
Výsledek na webu
—
DOI - Digital Object Identifier
—
Alternativní jazyky
Jazyk výsledku
angličtina
Název v původním jazyce
Efficiently Reusing Old Models Across Languages via Transfer Learning
Popis výsledku v původním jazyce
Recent progress in neural machine translation is directed towards larger neural networks trained on an increasing amount of hardware resources. As a result, NMT models are costly to train, both financially, due to the electricity and hardware cost, and environmentally, due to the carbon footprint. It is especially true in transfer learning for its additional cost of training the ''parent'' model before transferring knowledge and training the desired ''child'' model. In this paper, we propose a simple method of re-using an already trained model for different language pairs where there is no need for modifications in model architecture. Our approach does not need a separate parent model for each investigated language pair, as it is typical in NMT transfer learning. To show the applicability of our method, we recycle a Transformer model trained by different researchers and use it to seed models for different language pairs. We achieve better translation quality and shorter convergence times than when tra
Název v anglickém jazyce
Efficiently Reusing Old Models Across Languages via Transfer Learning
Popis výsledku anglicky
Recent progress in neural machine translation is directed towards larger neural networks trained on an increasing amount of hardware resources. As a result, NMT models are costly to train, both financially, due to the electricity and hardware cost, and environmentally, due to the carbon footprint. It is especially true in transfer learning for its additional cost of training the ''parent'' model before transferring knowledge and training the desired ''child'' model. In this paper, we propose a simple method of re-using an already trained model for different language pairs where there is no need for modifications in model architecture. Our approach does not need a separate parent model for each investigated language pair, as it is typical in NMT transfer learning. To show the applicability of our method, we recycle a Transformer model trained by different researchers and use it to seed models for different language pairs. We achieve better translation quality and shorter convergence times than when tra
Klasifikace
Druh
D - Stať ve sborníku
CEP obor
—
OECD FORD obor
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Návaznosti výsledku
Projekt
Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.
Návaznosti
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Ostatní
Rok uplatnění
2020
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Údaje specifické pro druh výsledku
Název statě ve sborníku
Proceedings of the 22st Annual Conference of the European Association for Machine Translation (2020)
ISBN
978-989-33-0589-8
ISSN
—
e-ISSN
—
Počet stran výsledku
10
Strana od-do
1-10
Název nakladatele
European Association for Machine Translation
Místo vydání
Lisboa, Portugal
Místo konání akce
Lisboa, Portugal
Datum konání akce
3. 11. 2020
Typ akce podle státní příslušnosti
WRD - Celosvětová akce
Kód UT WoS článku
—