Arabizi vs LLMs: Can the Genie Understand the Language of Aladdin?

• URL: http://arxiv.org/abs/2502.20973v1
• Date: Fri, 28 Feb 2025 11:37:52 GMT
• Title: Arabizi vs LLMs: Can the Genie Understand the Language of Aladdin?
• Authors: Perla Al Almaoui, Pierrette Bouillon, Simon Hengchen,
• Abstract summary: Arabizi is a hybrid form of Arabic that incorporates Latin characters and numbers.<n>It poses significant challenges for machine translation due to its lack of formal structure.<n>This research project investigates the model's performance in translating Arabizi into both Modern Standard Arabic and English.
• Score: 0.4751886527142778
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: In this era of rapid technological advancements, communication continues to evolve as new linguistic phenomena emerge. Among these is Arabizi, a hybrid form of Arabic that incorporates Latin characters and numbers to represent the spoken dialects of Arab communities. Arabizi is widely used on social media and allows people to communicate in an informal and dynamic way, but it poses significant challenges for machine translation due to its lack of formal structure and deeply embedded cultural nuances. This case study arises from a growing need to translate Arabizi for gisting purposes. It evaluates the capacity of different LLMs to decode and translate Arabizi, focusing on multiple Arabic dialects that have rarely been studied up until now. Using a combination of human evaluators and automatic metrics, this research project investigates the model's performance in translating Arabizi into both Modern Standard Arabic and English. Key questions explored include which dialects are translated most effectively and whether translations into English surpass those into Arabic.

Related papers

• LLM Alignment for the Arabs: A Homogenous Culture or Diverse Ones? [2.7195102129095003]
  Large language models (LLMs) have the potential of being useful tools that can automate tasks and assist humans. These models are more fluent in English and more aligned with Western cultures, norms, and values. Arabs are sometimes assumed to share the same culture.
  arXiv  Detail & Related papers  (2025-03-19T08:52:59Z)
• AIN: The Arabic INclusive Large Multimodal Model [71.29419186696138]
  AIN is an English-Arabic bilingual LMM designed to excel in English and Arabic. AIN demonstrates state-of-the-art Arabic performance, while also possessing strong English-language visual capabilities. AIN's superior capabilities position it as a significant step toward empowering Arabic speakers with advanced multimodal generative AI tools.
  arXiv  Detail & Related papers  (2025-01-31T18:58:20Z)
• A Survey of Code-switched Arabic NLP: Progress, Challenges, and Future Directions [33.45834558604992]
  We provide a review of the current literature in the field of code-switched Arabic NLP.<n>The widespread occurrence of code-switching across the region makes it vital to address these linguistic needs when developing language technologies.
  arXiv  Detail & Related papers  (2025-01-23T06:46:23Z)
• On The Origin of Cultural Biases in Language Models: From Pre-training Data to Linguistic Phenomena [10.263201685476492]
  This paper aims to uncover the origins of entity-related cultural biases in Language Models (LMs) We introduce CAMeL-2, a parallel Arabic-English benchmark of 58,086 entities associated with Arab and Western cultures and 367 masked natural contexts for entities. Our evaluations using CAMeL-2 reveal reduced performance gaps between cultures by LMs when tested in English compared to Arabic.
  arXiv  Detail & Related papers  (2025-01-08T18:15:47Z)
• Second Language (Arabic) Acquisition of LLMs via Progressive Vocabulary Expansion [55.27025066199226]
  This paper addresses the need for democratizing large language models (LLM) in the Arab world.<n>One practical objective for an Arabic LLM is to utilize an Arabic-specific vocabulary for the tokenizer that could speed up decoding.<n>Inspired by the vocabulary learning during Second Language (Arabic) Acquisition for humans, the released AraLLaMA employs progressive vocabulary expansion.
  arXiv  Detail & Related papers  (2024-12-16T19:29:06Z)
• AraDiCE: Benchmarks for Dialectal and Cultural Capabilities in LLMs [22.121471902726892]
  We present AraDiCE, a benchmark for Arabic Dialect and Cultural Evaluation.<n>First-ever fine-grained benchmark designed to evaluate cultural awareness across the Gulf, Egypt, and Levant regions.
  arXiv  Detail & Related papers  (2024-09-17T17:59:25Z)
• Bilingual Adaptation of Monolingual Foundation Models [48.859227944759986]
  We present an efficient method for adapting a monolingual Large Language Model (LLM) to another language. Our two-stage approach begins with expanding the vocabulary and training only the embeddings matrix. By continually pre-training on a mix of Arabic and English corpora, the model retains its proficiency in English while acquiring capabilities in Arabic.
  arXiv  Detail & Related papers  (2024-07-13T21:09:38Z)
• ArabicMMLU: Assessing Massive Multitask Language Understanding in Arabic [51.922112625469836]
  We present datasetname, the first multi-task language understanding benchmark for the Arabic language. Our data comprises 40 tasks and 14,575 multiple-choice questions in Modern Standard Arabic (MSA) and is carefully constructed by collaborating with native speakers in the region. Our evaluations of 35 models reveal substantial room for improvement, particularly among the best open-source models.
  arXiv  Detail & Related papers  (2024-02-20T09:07:41Z)
• AceGPT, Localizing Large Language Models in Arabic [73.39989503874634]
  The paper proposes a comprehensive solution that includes pre-training with Arabic texts, Supervised Fine-Tuning (SFT) utilizing native Arabic instructions, and GPT-4 responses in Arabic. The goal is to cultivate culturally cognizant and value-aligned Arabic LLMs capable of accommodating the diverse, application-specific needs of Arabic-speaking communities.
  arXiv  Detail & Related papers  (2023-09-21T13:20:13Z)
• TARJAMAT: Evaluation of Bard and ChatGPT on Machine Translation of Ten Arabic Varieties [18.73290429469502]
  We assess Bard and ChatGPT regarding their machine translation proficiencies across ten varieties of Arabic. Our evaluation covers diverse Arabic varieties such as Classical Arabic (CA), Modern Standard Arabic (MSA), and several country-level dialectal variants. On CA and MSA, instruction-tuned LLMs, however, trail behind commercial systems such as Google Translate.
  arXiv  Detail & Related papers  (2023-08-06T08:29:16Z)
• Beyond Arabic: Software for Perso-Arabic Script Manipulation [67.31374614549237]
  We provide a set of finite-state transducer (FST) components and corresponding utilities for manipulating the writing systems of languages that use the Perso-Arabic script. The library also provides simple FST-based romanization and transliteration.
  arXiv  Detail & Related papers  (2023-01-26T20:37:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.