151 citations · 310 across the 18 of their papers we have counts for
20 papers
When Similar Means Different: Evaluating LLMs on Arabic--Hebrew Cognates
Junhong Liang, Noor Abo Mokh, Bashar Alhafni
Arabic and Hebrew, as closely related Semitic languages, share many words with similar surface forms, including true cognates, false friends, and modern loanwords. These lexical re…
Arabic Sentence Segmentation Across Genres and Punctuation Conditions
Mohammed Elkholy, Khalid N. Elmadani, Nizar Habash +1
Sentence segmentation in Arabic is challenging due to ambiguous and inconsistent punctuation, with many texts lacking reliable sentence boundary markers. Existing approaches rely h…
Arabic Morphosyntactic Tagging and Dependency Parsing with Large Language Models
Mohamed Adel, Bashar Alhafni, Nizar Habash
LLMs perform strongly across NLP, but their ability to produce explicit grammatical analyses remains unclear. Arabic provides a challenging testbed due to its rich morphology and o…
Global PIQA: Evaluating Commonsense Reasoning Across 100+ Languages and Cultures
Tyler A. Chang, Catherine Arnett, Abdelrahman Sadallah +377
To date, there exist almost no culturally-specific evaluation benchmarks for large language models (LLMs) that cover a large number of languages and cultures. In this paper, we pre…
BALSAM: A Platform for Benchmarking Arabic Large Language Models
Rawan Al-Matham, Kareem Darwish, Raghad Al-Rasheed +40
The impressive advancement of Large Language Models (LLMs) in English has not been matched across all languages. In particular, LLM performance in Arabic lags behind, due to data s…
Opportunities and Challenges of LLMs in Education: An NLP Perspective
Sowmya Vajjala, Bashar Alhafni, Stefano Bannò +2
Interest in the role of large language models (LLMs) in education is increasing, considering the new opportunities they offer for teaching, learning, and assessment. In this paper,…
ARWI: Arabic Write and Improve
Kirill Chirkunov, Bashar Alhafni, Chatrine Qwaider +2
Although Arabic is spoken by over 400 million people, advanced Arabic writing assistance tools remain limited. To address this gap, we present ARWI, a new writing assistant that he…
Enhancing Text Editing for Grammatical Error Correction: Arabic as a Case Study
Bashar Alhafni, Nizar Habash
Text editing frames grammatical error correction (GEC) as a sequence tagging problem, where edit tags are assigned to input tokens, and applying these edits results in the correcte…
Strategies for Arabic Readability Modeling
Juan Piñeros Liberato, Bashar Alhafni, Muhamed Al Khalil +1
Automatic readability assessment is relevant to building NLP applications for education, content analysis, and accessibility. However, Arabic readability assessment is a challengin…
Exploiting Dialect Identification in Automatic Dialectal Text Normalization
Bashar Alhafni, Sarah Al-Towaity, Ziyad Fawzy +4
Dialectal Arabic is the primary spoken language used by native Arabic speakers in daily communication. The rise of social media platforms has notably expanded its use as a written…
Perception, performance, and detectability of conversational artificial intelligence across 32 university courses
Hazem Ibrahim, Fengyuan Liu, Rohail Asim +36
The emergence of large language models has led to the development of powerful tools such as ChatGPT that can produce text indistinguishable from human-generated work. With the incr…
Advancements in Arabic Grammatical Error Detection and Correction: An Empirical Investigation
Bashar Alhafni, Go Inoue, Christian Khairallah +1
Grammatical error correction (GEC) is a well-explored problem in English with many existing models and datasets. However, research on GEC in morphologically rich languages has been…
CrisisLTLSum: A Benchmark for Local Crisis Event Timeline Extraction and Summarization
Hossein Rajaby Faghihi, Bashar Alhafni, Ke Zhang +3
Social media has increasingly played a key role in emergency response: first responders can use public posts to better react to ongoing crisis events and deploy the necessary resou…
The Shared Task on Gender Rewriting
Bashar Alhafni, Nizar Habash, Houda Bouamor +11
In this paper, we present the results and findings of the Shared Task on Gender Rewriting, which was organized as part of the Seventh Arabic Natural Language Processing Workshop. T…
Arabic Word-level Readability Visualization for Assisted Text Simplification
Reem Hazim, Hind Saddiki, Bashar Alhafni +2
This demo paper presents a Google Docs add-on for automatic Arabic word-level readability visualization. The add-on includes a lemmatization component that is connected to a five-l…
The User-Aware Arabic Gender Rewriter
Bashar Alhafni, Ossama Obeid, Nizar Habash
We introduce the User-Aware Arabic Gender Rewriter, a user-centric web-based system for Arabic gender rewriting in contexts involving two users. The system takes either Arabic or E…
User-Centric Gender Rewriting
Bashar Alhafni, Nizar Habash, Houda Bouamor
In this paper, we define the task of gender rewriting in contexts involving two users (I and/or You) - first and second grammatical persons with independent grammatical gender pref…
The Arabic Parallel Gender Corpus 2.0: Extensions and Analyses
Bashar Alhafni, Nizar Habash, Houda Bouamor
Gender bias in natural language processing (NLP) applications, particularly machine translation, has been receiving increasing attention. Much of the research on this issue has foc…
The Interplay of Variant, Size, and Task Type in Arabic Pre-trained Language Models
Go Inoue, Bashar Alhafni, Nurpeiis Baimukan +2
In this paper, we explore the effects of language variants, data sizes, and fine-tuning task types in Arabic pre-trained language models. To do so, we build three pre-trained langu…
Contextualized Word Embeddings Enhanced Event Temporal Relation Extraction for Story Understanding
Rujun Han, Mengyue Liang, Bashar Alhafni +1
Learning causal and temporal relationships between events is an important step towards deeper story and commonsense understanding. Though there are abundant datasets annotated with…