Page: 1 2 3 4 5 6 7... 169
41 |
AraConv: Developing an Arabic Task-Oriented Dialogue System Using Multi-Lingual Transformer Model mT5
|
|
|
|
In: Applied Sciences; Volume 12; Issue 4; Pages: 1881 (2022)
|
|
BASE
|
|
Show details
|
|
42 |
Segmental and Prosodic Evidence for Property-by-Property Transfer in L3 English in Northern Africa
|
|
|
|
In: Languages; Volume 7; Issue 1; Pages: 28 (2022)
|
|
BASE
|
|
Show details
|
|
45 |
A Survey of Al-Jumal Al-Ashartiyyah (The Conditional Sentences) in Arabic Language ...
|
|
|
|
BASE
|
|
Show details
|
|
46 |
A Survey of Al-Jumal Al-Ashartiyyah (The Conditional Sentences) in Arabic Language ...
|
|
|
|
BASE
|
|
Show details
|
|
47 |
Education and COVID-19: Learning Arabic Language and Perspectives
|
|
|
|
BASE
|
|
Show details
|
|
48 |
Female rap in Arab countries. The case of Mayam Mahmoud ; Rap femenino en países árabes. El caso de Mayam Mahmoud
|
|
|
|
BASE
|
|
Show details
|
|
49 |
Beginning Moroccan Arabic (Darija): An OER Multimedia Textbook
|
|
|
|
BASE
|
|
Show details
|
|
50 |
Advanced Moroccan Arabic (Darija): An OER Multimedia Textbook
|
|
|
|
BASE
|
|
Show details
|
|
52 |
Metaphors of cancer in the Arabic language: An analysis of the use of metaphors in the online narratives of breast cancer patients
|
|
|
|
In: Open Linguistics, Vol 8, Iss 1, Pp 27-45 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
53 |
Deceptive Opinions Detection Using New Proposed Arabic Semantic Features
|
|
|
|
In: ISSN: 1877-0509 ; EISSN: 1877-0509 ; Procedia Computer Science ; https://hal.archives-ouvertes.fr/hal-03299022 ; Procedia Computer Science, Elsevier, 2021, 189, pp.29 - 36. ⟨10.1016/j.procs.2021.05.067⟩ (2021)
|
|
BASE
|
|
Show details
|
|
54 |
Transcultural and familial factors in bilingualism and language transmission: A qualitative study of maternal representations of French-Maghrebi Arabic bilingual children
|
|
|
|
In: ISSN: 1363-4615 ; Transcultural Psychiatry ; https://hal.archives-ouvertes.fr/hal-03487806 ; Transcultural Psychiatry, SAGE Publications, 2021, 58 (6), pp.804-816. ⟨10.1177/13634615211011846⟩ (2021)
|
|
BASE
|
|
Show details
|
|
55 |
Integrating L1 in L2 Classrooms: The Case of Arabic as a Foreign Language in US Universities
|
|
|
|
In: Faculty Journal Articles (2021)
|
|
BASE
|
|
Show details
|
|
56 |
Variation et représentation linguistique dans la variété arabe d'Ouezzane: lorsque le quantitative n'explique pas tout
|
|
|
|
BASE
|
|
Show details
|
|
57 |
An Arabic Transformation Based Approach to Automatic Paraphrasing of Syntactic Sentences
|
|
|
|
In: ISSN: 1539-8072 ; Sino-US English Teaching ; https://hal.archives-ouvertes.fr/hal-03280191 ; Sino-US English Teaching, 2021, 18 (6), pp.137-146. ⟨10.17265/1539-8072/2021.06.001⟩ (2021)
|
|
BASE
|
|
Show details
|
|
58 |
Sentiment Analysis of Arabic Documents
|
|
|
|
In: Natural Language Processing for Global and Local Business ; https://hal.archives-ouvertes.fr/hal-03124729 ; Fatih Pinarbasi; M. Nurdan Taskiran. Natural Language Processing for Global and Local Business, pp.307-331, 2021, 9781799842408. ⟨10.4018/978-1-7998-4240-8.ch013⟩ ; https://www.igi-global.com/ (2021)
|
|
BASE
|
|
Show details
|
|
59 |
Pattern borrowing and hybridization in Mubi (East Chadic): The importance of congruence
|
|
|
|
In: ISSN: 1750-1245 ; EISSN: 1755-2036 ; Word Structure ; https://halshs.archives-ouvertes.fr/halshs-03507468 ; Word Structure, [Edinburgh]: Edinburgh University Press, 2021, Morphology in Contact, 14 (2), pp.246-270. ⟨10.3366/word.2021.0189⟩ (2021)
|
|
BASE
|
|
Show details
|
|
60 |
Improving Machine Translation of Arabic Dialects through Multi-Task Learning
|
|
|
|
In: 20th International Conference Italian Association for Artificial Intelligence:AIxIA 2021 ; https://hal.archives-ouvertes.fr/hal-03435996 ; 20th International Conference Italian Association for Artificial Intelligence:AIxIA 2021, Dec 2021, MILAN/Virtual, Italy (2021)
|
|
Abstract:
International audience ; Neural Machine Translation (NMT) systems have been shown to perform impressively on many language pairs compared to Statistical Machine Translation (SMT). However, these systems are data-intensive, which is problematic for the majority of language pairs, and especially for low-resource languages. In this work, we address this issue in the case of certain Arabic dialects, those variants of Modern Standard Arabic (MSA) that are spelling non-standard, morphologically rich, and yet resource-poor variants. Here, we have experimented with several multitasking learning strategies to take advantage of the relationships between these dialects. Despite the simplicity of this idea, empirical results show that several multitasking learning strategies are capable of achieving remarkable performance compared to statistical machine translation. For instance, we obtained the BLUE scores for the Algerian → Modern-Standard-Arabic and the Moroccan → Palestinian of 35.06 and 27.55, respectively, while the scores obtained with a statistical method are 15.1 and 18.91 respectively. We show that on 42 machine translation experiments, and despite the use of a small corpus, multitasking learning achieves better performance than statistical machine translation in 88% of cases.
|
|
Keyword:
[INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]; Arabic dialects; Lowresource Languages; Machine Translation; Multitask Learning; Neural Network
|
|
URL: https://hal.archives-ouvertes.fr/hal-03435996 https://hal.archives-ouvertes.fr/hal-03435996/document https://hal.archives-ouvertes.fr/hal-03435996/file/Springer_Lecture_Notes_in_Computer_Science__4_.pdf
|
|
BASE
|
|
Hide details
|
|
Page: 1 2 3 4 5 6 7... 169
|
|