The Quest for NLP Applications and Tools: The Case of Standard Arabic and the Dialects

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F21%3A10441744" target="_blank" >RIV/00216208:11320/21:10441744 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/IALP54817.2021.9675225" target="_blank" >https://doi.org/10.1109/IALP54817.2021.9675225</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/IALP54817.2021.9675225" target="_blank" >10.1109/IALP54817.2021.9675225</a>

Jazyk výsledku

angličtina

Název v původním jazyce

The Quest for NLP Applications and Tools: The Case of Standard Arabic and the Dialects

Popis výsledku v původním jazyce

The rapid advances of natural language processing (NLP) research bring about applications and tools that serve automating Arabic at different linguistic levels. However, there is a focus on the modern standard Arabic (MSA) more than the dialects which are used heavily in day-to-day communication and require special handling. This paper introduces research efforts in Arabic NLP with emphasis on tools, applications, and resources related to core NLP areas. Some research and scholarly work come from researchers working on extended projects to compute Arabic. The findings demonstrated that research on Arabic NLP can be characterized by emphasis on morphological analysis and processing of MSA especially tokenization and tagging. Recently there has been a growing interest in processing and identifying Arabic dialects. The proposed solutions were adapted from other solutions used for MSA or designed mainly for certain dialects. Also, advances in developing transformers were applied to Arabic NLP in limited research. It appeared that ambiguity is still a big challenge to overcome and there is a need to innovate applications and tools for Arabic MSA and the dialects in parallel.

Název v anglickém jazyce

The Quest for NLP Applications and Tools: The Case of Standard Arabic and the Dialects

Popis výsledku anglicky

The rapid advances of natural language processing (NLP) research bring about applications and tools that serve automating Arabic at different linguistic levels. However, there is a focus on the modern standard Arabic (MSA) more than the dialects which are used heavily in day-to-day communication and require special handling. This paper introduces research efforts in Arabic NLP with emphasis on tools, applications, and resources related to core NLP areas. Some research and scholarly work come from researchers working on extended projects to compute Arabic. The findings demonstrated that research on Arabic NLP can be characterized by emphasis on morphological analysis and processing of MSA especially tokenization and tagging. Recently there has been a growing interest in processing and identifying Arabic dialects. The proposed solutions were adapted from other solutions used for MSA or designed mainly for certain dialects. Also, advances in developing transformers were applied to Arabic NLP in limited research. It appeared that ambiguity is still a big challenge to overcome and there is a need to innovate applications and tools for Arabic MSA and the dialects in parallel.

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)

Projekt

—

Návaznosti

—

Rok uplatnění

2021

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

2021 International Conference on Asian Language Processing, IALP 2021

ISBN

978-1-66548-311-7

ISSN

—

e-ISSN

—

Počet stran výsledku

7

Strana od-do

222-228

Název nakladatele

IEEE Conference Publishing Services

Místo vydání

Piscataway

Místo konání akce

Singapur

Datum konání akce

11. 12. 2021

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—