salam khalifa

PhD candidate at @SBU_linguistics and @IACSComputes | Formerly @camelnlp | ال+صرف

Managing @_ArabicNLP account

[Nizar Habash @NYHabash]

هذه الدراسة ما زالت مستمرة... الرجاء المشاركة.

[CAMeL Lab | «مختبر «كامل @CamelNlp]

📢 Shared Task on Arabic Sentence Segmentation @ the 4th Arabic NLP Conference (https://t.co/mOBFXvDgLQ) 📢

The shared task focuses on segmenting Arabic documents into coherent sentences. Given an Arabic document as input, participating systems must identify sentence boundaries throughout the text. The task is formulated as a binary token classification problem, where models predict whether a sentence boundary follows each token.

Participating teams are welcome to take part in any number of tasks/tracks, and those who take part in the official test phase on CodaBench will present their work at 4th Arabic NLP Conference @_ArabicNLP, co-located with EMNLP 2026 @emnlpmeeting, as well as have a publication included in the official proceedings.

🏆 Awards will be given to top-performing systems 🏆

Organizers: @moelkholy1304, @khalid_elmadani, @NYHabash and @balhafni

#ArabicNLP #EMNLP2026

[ACLRollingReview @ReviewAcl]

📢 ARR-May reviewers can now try REVAS, an experimental review support tool.
REVAS gives feedback on review quality criteria and ARR reviewer heuristics, but does not suggest review content or scores.
🔗 https://t.co/MOysgnz4UQ
#ARR #EMNLP #ACL #NLProc

[EMNLP 2026 @emnlpmeeting]

⚠️ Submitting to EMNLP 2026? Make sure to review our newly published Paper Integrity Policy first! It includes important updates on Generative Assistance in Authorship, thinly sliced contributions, and unverifiable references.

🔗 Details: https://t.co/UjG6zbQnaz

#EMNLP2026

[Tuhin Chakrabarty @TuhinChakr]

Looking for 1 emergency reviewer for a
@COLM_conf paper on Image Editing of Diffusion Model due Wednesday (05/20). Please DM me if interested. Thanks!

Retweets appreciated

[Thomas G. Dietterich @tdietterich]

Attention @arxiv authors: Our Code of Conduct states that by signing your name as an author of a paper, each author takes full responsibility for all its contents, irrespective of how the contents were generated. 1/

[salam khalifa @salamkhalifa]

"An author who fabricates a citation commits a serious breach of ethics, and using an automated system as a proxy to generate such citations is equally unacceptable."

[ACL 2026 @aclmeeting]

Some of you may have heard about the desk-rejected papers from the ACL'26/ARR Jan26 or Oct25 cycles because of hallucinated references. These cases were detected post-commitment. ACL Program chairs have an official statement on this: https://t.co/O1usci13h2 #ACL2026NLP #NLProc

[EMNLP 2026 @emnlpmeeting]

Submitting to ARR for #EMNLP2026? We're running an opt-in AI Reviewing Experiment. Help us test AI-generated reviews during your ARR submission. 🤖
✅ Reviewers, ACs, and SACs will not be able to see it
✅ Will not affect decisions

🔗 Read more: https://t.co/uHf1XKtE5j

[salam khalifa @salamkhalifa]

والله عيب!

[Nizar Habash @NYHabash]

AI-generated maps in a scientific conference talk are a bold choice… especially when the borders seem to have been peer-reviewed by hallucinating artificial stupidity.

Please don’t do this. Maps are not decorative filler: borders, place names, and regions carry real history, politics, and people.

يعني بالله عليكم، الخرائط مش ديكور نحطه ونعدّي. الحدود وأسماء الأماكن وراها تاريخ وسياسة وناس حقيقيين، فبلاش نسيبها لبرامج غباء اصطناعي بتهلوس.

[Nizar Habash @NYHabash]

Excited to present our work at the OSACT Workshop at #LREC2026 in Palma! 🇪🇸

📄 Parsing Arabic Dialects Revisited: New Benchmarks, Models, and Insights

We revisit dialectal Arabic dependency parsing using modern neural models and show that even small amounts of dialect-specific data can lead to substantial gains in parsing accuracy.

Highlights:
🔹 New annotated Gulf Arabic dataset
🔹 State-of-the-art multi-variety Arabic parser
🔹 New insights into training data and cross-dialect parsing performance

#ArabicNLP #NLP #ComputationalLinguistics #DialectalArabic @CamelNlp

[Nizar Habash @NYHabash]

Excited to present our work at the main conference of #LREC2026 in Palma! 🇪🇸

📄 A Bilingual Bimodal Benchmark for Arabic-English NLP Across Grammatical Correction, Essay Scoring, Morphological Tagging, and Speech Recognition

We introduce ZAEBUC*, a new bilingual and bimodal benchmark covering Arabic and English across both written and spoken language.

The benchmark supports multiple NLP tasks, including:
🔹 Grammatical Error Correction
🔹 Automated Essay Scoring
🔹 Morphological Tagging
🔹 Automatic Speech Recognition

ZAEBUC* enables cross-linguistic and cross-modal evaluation, with benchmarking experiments spanning traditional NLP models and LLMs.

#ArabicNLP #NLP #SpeechRecognition #LLM #ComputationalLinguistics @CamelNlp @balhafni

[Nizar Habash @NYHabash]

Excited to present our work at #LREC2026 in Palma! 🇪🇸

📄 DIALECTALARABICMMLU: Benchmarking Dialectal Capabilities in Arabic and Multilingual Language Models

We introduce DIALECTALARABICMMLU, a new benchmark for evaluating LLM performance across major Arabic dialects.

The benchmark extends MMLU-Redux with:
🔹 15K QA pairs across 5 Arabic dialects
🔹 32 academic and professional domains
🔹 Human-curated translations and adaptations
🔹 Evaluation of 19 Arabic and multilingual LLMs

Our results reveal substantial variation in model performance across dialects, highlighting persistent gaps in dialectal understanding and generalization.

Dataset: https://t.co/vw77ZQjOhw

#ArabicNLP #LLM #DialectalArabic #NLP #ComputationalLinguistics @AltakroriM @cigilt @preslav_nakov @AlhamFikri

[Nizar Habash @NYHabash]

Excited to present our work at #LREC2026 in Palma! 🇪🇸

📄 A Large and Balanced Multi-Domain Arabic Corpus Annotated for Morphology, Syntax, and Readability

We introduce BAREC-10M, a major expansion of the Balanced Arabic Readability Evaluation Corpus, growing from 1M to 10M words with rich linguistic annotations and broad multi-domain coverage.

Highlights:
🔹 45 sub-corpora across diverse domains and genres
🔹 Morphological, syntactic, and readability annotations
🔹 Coverage of news, literature, educational and children’s texts, religious discourse, and more
🔹 Balanced resource for studying Arabic variation, style, and complexity

We hope BAREC-10M will support future research in Arabic NLP, readability, education, and linguistic analysis.

Resource: https://t.co/ZBh5McJEP0

#LREC2026 #ArabicNLP #ComputationalLinguistics #CorpusLinguistics #NLP @HanadaEducation @CamelNlp

[Nizar Habash @NYHabash]

Excited to present our work at #LREC2026 in Palma! 🇪🇸

📄 Benchmarking Arabic Authorship Attribution and Style Transfer with Large Language Models

We revisit two important style-centric NLP tasks for Arabic:
🔹 Authorship Attribution
🔹 Authorship Style Transfer
Our work introduces:
🔹 A new dataset covering Modern Standard and Dialectal Arabic
🔹 Transformer-based AA models with contrastive learning
🔹 Human evaluation of model performance
🔹 A benchmark of LLMs on Arabic style recognition and generation

Our findings reveal important limitations in current LLMs’ ability to model Arabic writing style, while providing new resources to support future research in this area.

#LREC2026 #ArabicNLP #LLM #AuthorshipAttribution #StyleTransfer #NLP @injy_hamed @balhafni @thamar_solorio

[ArabicNLP2026 @_ArabicNLP]

Great news for the Arabic NLP community! 🎉

📢 Call for Shared Task Proposals is now open!

الإعلان الأول للدعوة لتقديم (Shared Tasks) ضمن المؤتمر الرابع للمعالجة الآلية للغة العربية ArabicNLP 2026، والذي سيُعقد بالتزامن مع EMNLP 2026 في بودابست، هنغاريا، خلال الفترة 24–29 أكتوبر 2026.

🗓️ آخر موعد لتقديم Shared Tasks: 25 أبريل 2026
✅ إشعارات القبول: 2 مايو 2026
🔗 رابط التقديم:
https://t.co/iaZlQGSzHy

Great news for the Arabic NLP community! 🎉
📢 Call for Shared Task Proposals is now open!

The first call for Shared Task Proposals for ArabicNLP 2026 is now out. The Fourth Arabic Natural Language Processing Conference will be co-located with EMNLP 2026 in Budapest, Hungary, on October 24–29, 2026.

🗓️ Shared Task proposal submission deadline: April 25, 2026
✅ Notification of acceptance: May 2, 2026

🔗 Submission link:
https://t.co/iaZlQGSzHy

#ArabicNLP2026 #ArabicNLP #SharedTasks #ArabicNLPSharedTasks #EMNLP2026

[ArabicNLP2026 @_ArabicNLP]

Second Call For Papers is out!

- Abstract submission deadline: June 18th, 2026
- Full paper submission deadline: June 25th, 2026

Visit our website for more information on submission instructions: https://t.co/zBrgbibzOs

[salam khalifa @salamkhalifa]

If you are at #EACL2026 (in-person or virtual), stop by TODAY at our presentation of the "Computational Benchmarks for Egyptian Arabic Child Directed Speech"
(11:30 Rabat local time)
@SBU_linguistics @IACSComputes @CamelNlp
@qaddoumi_a @OwenRambow
https://t.co/o7zWBZNjJq

[eaclmeeting @eaclmeeting]

🎤 Keynote at #EACL2026

Speaker: Nizar Habash
Title: “Arabic and Technology: A 40-Year Perspective”

Don’t miss this keynote tomorrow in Session 1: Plenary (10:00–11:00), right after the conference opening session!

[salam khalifa @salamkhalifa]

@joebradford May I suggest joining SIGARAB: https://t.co/pwOIBz9SfL

Most experts on the matter are on it. Our fourth ArabicNLP conference will be in October.

[ArabicNLP2026 @_ArabicNLP]

المؤتمر الرابع للمعالجة الآلية للغة العربية ArabicNLP 2026 سيُعقد بالتزامن مع مؤتمر EMNLP 2026 في بودابست، هنغاريا (أكتوبر 2026) 🎉

📢 الإعلان الأول للدعوة لتقديم الأوراق (CFP):
15 مارس 2026
ترقبوا المزيد من التفاصيل قريبًا!

Great News! The Fourth Arabic Natural Language Processing Conference (ArabicNLP 2026) will be co-located with EMNLP 2026 in Budapest, Hungary (October 2026) 🎉

📢 First Call for Papers: March 15, 2026

#ArabicNLP2026 #ArabicNLP #EMNLP
Stay tuned for more updates!