2 |
A Transformer-Based Neural Machine Translation Model for Arabic Dialects That Utilizes Subword Units
|
|
|
|
In: Sensors ; Volume 21 ; Issue 19 (2021)
|
|
Abstract:
Languages that allow free word order, such as Arabic dialects, are of significant difficulty for neural machine translation (NMT) because of many scarce words and the inefficiency of NMT systems to translate these words. Unknown Word (UNK) tokens represent the out-of-vocabulary words for the reason that NMT systems run with vocabulary that has fixed size. Scarce words are encoded completely as sequences of subword pieces employing the Word-Piece Model. This research paper introduces the first Transformer-based neural machine translation model for Arabic vernaculars that employs subword units. The proposed solution is based on the Transformer model that has been presented lately. The use of subword units and shared vocabulary within the Arabic dialect (the source language) and modern standard Arabic (the target language) enhances the behavior of the multi-head attention sublayers for the encoder by obtaining the overall dependencies between words of input sentence for Arabic vernacular. Experiments are carried out from Levantine Arabic vernacular (LEV) to modern standard Arabic (MSA) and Maghrebi Arabic vernacular (MAG) to MSA, Gulf–MSA, Nile–MSA, Iraqi Arabic (IRQ) to MSA translation tasks. Extensive experiments confirm that the suggested model adequately addresses the unknown word issue and boosts the quality of translation from Arabic vernaculars to Modern standard Arabic (MSA).
|
|
Keyword:
Arabic dialects; modern standard Arabic; multi-head attention; neural machine translation (NMT); self-attention; shared vocabulary; subword units; transformer
|
|
URL: https://doi.org/10.3390/s21196509
|
|
BASE
|
|
Hide details
|
|
3 |
Complete Variable-Length Codes: An Excursion into Word Edit Operations
|
|
|
|
In: LATA 2020 ; https://hal.archives-ouvertes.fr/hal-02389403 ; LATA 2020, Mar 2020, Milan, Italy (2020)
|
|
BASE
|
|
Show details
|
|
4 |
Acoustic Data-Driven Subword Units Obtained through Segment Embedding and Clustering for Spontaneous Speech Recognition
|
|
|
|
In: Applied Sciences ; Volume 10 ; Issue 6 (2020)
|
|
BASE
|
|
Show details
|
|
5 |
Subunits Inference and Lexicon Development Based on Pairwise Comparison of Utterances and Signs
|
|
|
|
In: Information ; Volume 10 ; Issue 10 (2019)
|
|
BASE
|
|
Show details
|
|
6 |
Learning Subword Embedding to Improve Uyghur Named-Entity Recognition
|
|
|
|
In: Information ; Volume 10 ; Issue 4 (2019)
|
|
BASE
|
|
Show details
|
|
9 |
Using pronunciation-based morphological subword units to improve OOV handling in keyword search
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Quotient Complexity of Bifix-, Factor-, and Subword-Free Regular Language
|
|
|
|
BASE
|
|
Show details
|
|
11 |
An STD system for OOV query terms using various subword units
|
|
|
|
In: http://research.nii.ac.jp/ntcir/workshop/OnlineProceedings9/NTCIR/10-NTCIR9-SpokenDoc-SaitoH.pdf (2011)
|
|
BASE
|
|
Show details
|
|
12 |
Contextual verification for open vocabulary spoken term detection
|
|
|
|
In: Fraunhofer IAIS (2011)
|
|
BASE
|
|
Show details
|
|
13 |
Volkov, Modular and threshold subword counting and matrix representations of finite monoids
|
|
|
|
In: http://www.fc.up.pt/cmup/home/jalmeida/preprints/radicalshort2.pdf (2005)
|
|
BASE
|
|
Show details
|
|
14 |
Verbumculus and the discovery of unusual words
|
|
|
|
In: Apostolico, A; Gong, F C; & Lonardi, S. (2004). Verbumculus and the discovery of unusual words. Journal of Computer Science and Technology, 19(1), 22 - 41. UC Riverside: Retrieved from: http://www.escholarship.org/uc/item/5m66k36w (2004)
|
|
BASE
|
|
Show details
|
|
15 |
On average sequence complexity � www.elsevier.com/locate/tcs
|
|
|
|
In: http://www.cs.ucr.edu/~stelo/papers/tcs04.pdf (2003)
|
|
BASE
|
|
Show details
|
|
16 |
SUBWORD LATENT SEMANTIC ANALYSIS FOR TEXTTILING-BASED AUTOMATIC STORY SEGMENTATION OF CHINESE BROADCAST NEWS
|
|
|
|
In: http://isca-speech.org/archive_open/archive_papers/iscslp2008/358.pdf
|
|
BASE
|
|
Show details
|
|
17 |
and
|
|
|
|
In: http://www.mimuw.edu.pl/~rytter/MYPAPERS/PSC08_journal.pdf
|
|
BASE
|
|
Show details
|
|
18 |
1 Performance Analysis of Instruction Set Architecture Extensions for Multimedia§
|
|
|
|
In: http://www.cs.berkeley.edu/~slingn/publications/mm_isa_perf/mm_isa_perf_msp3.pdf
|
|
BASE
|
|
Show details
|
|
19 |
Parikh Matrices and Words over Tertiary Ordered Alphabet
|
|
|
|
In: http://research.ijcaonline.org/volume85/number4/pxc3893069.pdf
|
|
BASE
|
|
Show details
|
|
20 |
Morph-Based Speech Recognition and Modeling of Out-of-Vocabulary Words Across Languages
|
|
|
|
In: http://www-speech.sri.com/cgi-bin/run-distill?papers/acm2007-morph-asr.ps.gz
|
|
BASE
|
|
Show details
|
|
|
|