Syntax-aware data augmentation for neural machine translation
Identifikátory výsledku
Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3AWKKPAJAI" target="_blank" >RIV/00216208:11320/23:WKKPAJAI - isvavai.cz</a>
Výsledek na webu
<a href="https://ieeexplore.ieee.org/abstract/document/10202198/" target="_blank" >https://ieeexplore.ieee.org/abstract/document/10202198/</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/TASLP.2023.3301214" target="_blank" >10.1109/TASLP.2023.3301214</a>
Alternativní jazyky
Jazyk výsledku
angličtina
Název v původním jazyce
Syntax-aware data augmentation for neural machine translation
Popis výsledku v původním jazyce
"Data augmentation is an effective method for the performance enhancement of neural machine translation (NMT) by generating additional bilingual data. In this article, we propose a novel data augmentation strategy for neural machine translation. Unlike existing data augmentation methods that simply modify words with the same probability across different sentences, we introduce a sentence-specific probability approach for word selection based on the syntactic roles of words in the sentence. Our motivation is to consider a linguistics-motivated method to obtain more ingenious language generation rather than relying on computation-motivated approaches only. We argue that high-quality aligned bilingual data is crucial for NMT, and only computation-motivated data augmentation is insufficient to provide good enough extra enhancement data. Our approach leverages dependency parse trees of input sentences to determine the selection probability of each word in the sentence using three different functions to calculate probabilities for words with different depths. Besides, our method also revises the probability for words considering the sentence length. We evaluate our methods on multiple translation tasks. The experimental results demonstrate that our proposed data augmentation method does effectively boost existing sentence-independent methods for significant improvement of performance on translation tasks. Furthermore, an ablation study shows that our method does select fewer essential words and preserves the syntactic structure."
Název v anglickém jazyce
Syntax-aware data augmentation for neural machine translation
Popis výsledku anglicky
"Data augmentation is an effective method for the performance enhancement of neural machine translation (NMT) by generating additional bilingual data. In this article, we propose a novel data augmentation strategy for neural machine translation. Unlike existing data augmentation methods that simply modify words with the same probability across different sentences, we introduce a sentence-specific probability approach for word selection based on the syntactic roles of words in the sentence. Our motivation is to consider a linguistics-motivated method to obtain more ingenious language generation rather than relying on computation-motivated approaches only. We argue that high-quality aligned bilingual data is crucial for NMT, and only computation-motivated data augmentation is insufficient to provide good enough extra enhancement data. Our approach leverages dependency parse trees of input sentences to determine the selection probability of each word in the sentence using three different functions to calculate probabilities for words with different depths. Besides, our method also revises the probability for words considering the sentence length. We evaluate our methods on multiple translation tasks. The experimental results demonstrate that our proposed data augmentation method does effectively boost existing sentence-independent methods for significant improvement of performance on translation tasks. Furthermore, an ablation study shows that our method does select fewer essential words and preserves the syntactic structure."
Klasifikace
Druh
J<sub>ost</sub> - Ostatní články v recenzovaných periodicích
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
—
Návaznosti
—
Ostatní
Rok uplatnění
2023
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Údaje specifické pro druh výsledku
Název periodika
"IEEE/ACM Transactions on Audio, Speech, and Language Processing"
ISSN
2329-9290
e-ISSN
—
Svazek periodika
""
Číslo periodika v rámci svazku
2023-3-16
Stát vydavatele periodika
US - Spojené státy americké
Počet stran výsledku
12
Strana od-do
2988 - 2999
Kód UT WoS článku
—
EID výsledku v databázi Scopus
—