China

Conversational question-answering (CQA) plays a crucial role in bridging the gap between human language and machine understanding, enabling more natural and interactive interactions with AI systems. In this work, we present the first results on open-domain Arabic CQA using deep learning. We introduce AraQReCC, a large-scale Arabic CQA dataset containing 9K conversations with 62K question-answer pairs, created by translating a subset of the QReCC dataset. To ensure data quality, we used COMET-based filtering and manual ratings from large language models (LLMs), such as GPT-4 and LLaMA, selecting conversations with COMET scores, along with LLM ratings of 4 or more. AraQReCC facilitates advanced research in Arabic CQA, improving clarity and relevance through question rewriting. We applied AraT5 for question rewriting and used BM25 and Dense Passage Retrieval (DPR) for passage retrieval. AraT5 is also used for question answering, completing the end-to-end system. Our experiments show that the best performance is achieved with DPR, attaining an F1 score of 21.51\% on the test set. While this falls short of the human upper bound of 40.22\%, it underscores the importance of question rewriting and quality-controlled data in enhancing system performance.

EMNLP 2025

Open-domain Arabic Conversational Question Answering with Question Rewriting

arabic cqa

arabic question answering

# Welcome everyone to ACL 2022!

The 60th Annual Meeting of the Association for Computational Linguistics is taking place May 22-27, 2022 as a hybrid event, in Dublin and online. We are happy to welcome all of you to this anniversary edition with an almost 50-50 in-person and virtual participation. 
The main conference program features oral presentations, in-person and virtual posters and demo sessions, a plenary session for our best paper presentations and awards, three amazing keynote events and two new initiatives of invited talks: Spotlight Talks for Young Rising Stars (STIRS) and The Next Big Idea Talks. Posters (including Findings of ACL 2022) and demos are grouped by areas for both the in-person and the virtual sessions. For the virtual component, the talks will be on Zoom and the posters and the demos will be in GatherTown. The Student Research Workshop will have an oral session and a poster session as part of Poster Session 1. The program also features eight Tutorials and 28 Workshops. 

 
We wish you a wonderful conference! 
[**The ACL 2022 Organizing Committee**](https://www.2022.aclweb.org/organisers)
 
[**Conference Handbook**](https://drive.google.com/file/d/1_BUCMfhMVrjG9E2e71aHdHeE28KSje0l/view?usp=sharing) 
[**Mini Handbook**](https://drive.google.com/file/d/1qlBKl0wzmlVF1oCeMQl3BahLd9nLP5Ce/view?usp=sharing) 
[**Posters and Demo guides**](https://drive.google.com/file/d/1UucMAoCNncIOaH1rMMDa0owuG9qgvJTG/view?usp=sharing)

ACL 2022

The Association for Computational Linguistics (ACL) is the premier international scientific and professional society for people working on computational problems involving human language, a field often referred to as either computational linguistics or natural language processing (NLP). 

workshop paper

## Welcome!
"I am excited to welcome you to this year’s edition of the Conference on Empirical Methods in Natural Language Processing! Importantly, it marks the 30th edition of EMNLP. With over 8,000 submissions, more than 3,000 accepted papers, and thousands of attendees, we have come a long way from that first
workshop, which had 14 accepted papers. As the field looks ahead, Suzhou is the fitting location for celebrating this milestone: rooted in a long literary tradition, yet modern and forward-looking, and home to a large share of the NLP community." 

*Message from the General Chair, Dirk Hovy*

Celebrate 30 Years of EMNLP! 
EMNLP 2025 will be held in Suzhou, China from November 5th to November 9th, 2025.

Classical Arabic represents a significant era that encompasses the golden age of Arab culture, philosophy, and scientific literature. With a broad consensus on the importance of translating these literatures to enrich knowledge dissemination across communities, the advent of large language models (LLMs) and translation systems offers promising tools to facilitate this goal. However, we have identified a scarcity of translation datasets in Classical Arabic, which are often limited in scope and topics, hindering the development of high-quality translation systems. In response, we present the ATHAR dataset, which comprises 66,000 high-quality classical Arabic to English translation samples that cover a wide array of topics including science, culture, and philosophy. Furthermore, we assess the performance of current state-of-the-art LLMs under various settings, concluding that there is a need for such datasets in current systems. Our findings highlight how models can benefit from fine-tuning or incorporating this dataset into their pretraining pipelines. The dataset is publicly available on the HuggingFace Data Hub: https://huggingface.co/datasets/mohamed-khalil/ATHAR

ATHAR: A High-Quality and Diverse Dataset for Classical Arabic to English Translation

For effective use in specific countries, Large Language Models (LLMs) need a strong grasp of local culture and core knowledge to ensure socially appropriate, context-aware, and factually correct responses. Existing Arabic and Saudi benchmarks are limited, focusing mainly on dialects or lifestyle, with little attention to deeper cultural or domain-specific alignment from authoritative sources. To address this gap and the challenge LLMs face with non-Western cultural nuance, this study introduces the Saudi-Alignment Benchmark. It consists of 874 manually curated questions across two core cultural dimensions: Saudi Cultural and Ethical Norms, and Saudi Domain Knowledge. These questions span multiple subcategories and use three formats to assess different goals with verified sources. Our evaluation reveals significant variance in LLM alignment. GPT-4 achieved the highest overall accuracy (83.3%), followed by ALLaM-7B (81.8%) and Llama-3.3-70B (81.6%), whereas Jais-30B exhibited a pronounced shortfall at 21.9%. Furthermore, multilingual LLMs excelled in norms; ALLaM-7B in domain knowledge. Considering the effect of question format, LLMs generally excelled in selected-response formats but showed weaker results on generative tasks, indicating that recognition-based benchmarks alone may overestimate cultural and contextual alignment. These findings highlight the need for tailored benchmarks and reveal LLMs’ limitations in achieving cultural grounding, particularly in underrepresented contexts like Saudi Arabia.

Saudi-Alignment Benchmark: Assessing LLMs Alignment with Cultural Norms and Domain Knowledge in the Saudi Context

Information Extraction tasks such as Named Entity Recognition and Relation Extraction are often developed using diverse tagsets and annotation guidelines. This presents major challenges for model generalization, cross-dataset evaluation, tool interoperability, and broader industry adoption. 
To address these issues, we propose an information extraction ontology, WojoodOntology, which covers a wide range of named entity types and relations. WojoodOntology serves as a semantic mediation framework that facilitates alignment across heterogeneous tagsets and annotation guidelines. We propose two ontology-based mapping methods: (i) as a set of mapping rules for uni-directional tagset alignment; and (ii) as ontology-based prompting, which incorporates the ontology concepts directly into prompts, enabling large language models (LLMs) to perform more effective and bi-directional mappings. Our experiments show a 15% improvement in out-of-domain mapping accuracy when using ontology-based prompting compared to rule-based methods. Furthermore, WojoodOntology is aligned with Schema.org and Wikidata, enabling interoperability with knowledge graphs and facilitating broader industry adoption. The WojoodOntology is open source and available at https://sina.birzeit.edu/wojood.

InExOntology - Ontology-Driven LLM Prompting for Unified Information Extraction Tasks

This paper presents a methodology for inserting phrases in Arabic poems to conform to a specific rhythm using ByT5, a byte-level multilingual transformer-based model. Our work discusses a rule-based grapheme-to-beat transformation tailored for extracting the rhythm from fully diacritized Arabic script. Our approach employs a conditional denoising objective to fine-tune ByT5, where the model reconstructs masked words to match a target rhythm. We adopt a curriculum learning strategy, pre-training on a general Arabic dataset before fine-tuning on poetic dataset, and explore cross-lingual transfer from English to Arabic. Experimental results demonstrate that our models achieve high rhythmic alignment while maintaining semantic coherence. The proposed model has the potential to be used in co-creative applications in the process of composing classical Arabic poems.

Tahḏīb: A Rhythm-Aware Phrase Insertion for Classical Arabic Poetry Composition

Video-to-text and text-to-video retrieval are dominated by English benchmarks. We introduce a three-stage framework, AutoArabic, utilizing state-of-the-art large language models (LLMs) to translate non-Arabic benchmarks into Modern Standard Arabic, reducing the manual revision required by nearly fourfold. Applying the framework to DiDeMo, a video retrieval benchmark produces DiDeMo-AR, an Arabic variant with 40,144 fluent Arabic descriptions. Our experiments indicate that Arabic localization preserves benchmark difficulty. We evaluate three post-editing budgets (zero/ flagged-only/ full) and find that performance improves monotonically with more post-editing, while the raw LLM output (zero-budget) remains usable.

AutoArabic: A Three-Stage Framework for Localizing Video-Text Retrieval Benchmarks

Arabic Word Sense Disambiguation (WSD) remains challenging due to the language’s rich morphology, polysemy, and lack of large annotated resources. This study benchmarks four generative Large Language Models (LLMs)—GPT-4o, LLaMA 3.1-8B, Qwen 2.5-7B, and Gemma 2-9B—on two public Arabic WSD datasets under both zero-shot and fine-tuned conditions. Results show that GPT-4o achieves the strongest zero-shot performance (79 % accuracy, 66% macro-F1), while parameter-efficient fine-tuning of open models via LoRA closes and surpasses this gap. Qwen 2.5-7B attains 90.77 % accuracy and 83.98 % F1 on Dataset A, and LLaMA 3.1-8B reaches 88.51 % accuracy and 69.41 % F1 on Dataset B. The findings demonstrate that medium-sized open LLMs can serve as competitive, reproducible baselines for Arabic sense-level understanding when modest supervision is applied.

Zero-Shot and Fine-Tuned Evaluation of Generative LLMs for Arabic Word Sense Disambiguation

Tool calling is a critical capability that allows Large Language Models (LLMs) to interact with external systems, significantly expanding their utility. However, research and resources for tool calling are predominantly English-centric, leaving a gap in our understanding of how to enable this functionality for other languages, such as Arabic. This paper investigates three key research questions: (1) the necessity of in-language (Arabic) tool-calling data versus relying on cross-lingual transfer, (2) the effect of general-purpose instruction tuning on tool-calling performance, and (3) the value of fine-tuning on specific, high-priority tools. To address these questions, we conduct extensive experiments using base and post-trained variants of an open-weight Arabic LLM. To enable this study, we bridge the resource gap by translating and adapting two open-source tool-calling datasets into Arabic. Our findings provide crucial insights into the optimal strategies for developing robust tool-augmented agents for Arabic.

Tool Calling for Arabic LLMs: Data Strategies and Instruction Tuning

North African Arabic dialects pose major NLP challenges due to high lexical variation, script diversity (Arabic/Latin), and frequent French code-switching. We introduce a phoneme-based normalization that harmonizes surface forms across varieties by mapping both Arabic and French into a simplified Latin representation.

We then pretrain BERT models exclusively on normalized Modern Standard Arabic and French, without using any dialectal data. The resulting models are evaluated on Named Entity Recognition (DzNER, DarNER, WikiFANE) and sentiment classification (TwiFil).

Our approach achieves state-of-the-art performance on several North African benchmarks and shows strong zero-shot generalization from MSA to Algerian NER (Ar_20k > dialect-pretrained models). Results demonstrate that standard-only pretraining with normalization is a viable and scalable solution for supporting underserved Arabic dialects.

Modeling North African Dialects from Standard Languages

Argument mining for Arabic remains underexplored, largely due to the scarcity of annotated corpora. To address this gap, we examine the effectiveness of cross-lingual transfer from English. Using the English Persuasive Essays (PE) corpus, annotated with argumentative components (Major Claim, Claim, and Premise), we explore several transfer strategies: training encoder-based multilingual and monolingual models on English data, machine-translated Arabic data, and their combination. We further assess the impact of annotation noise introduced during translation by manually correcting portions of the projected training data. In addition, we investigate the potential of prompting large language models (LLMs) for the task. Experiments on a manually corrected Arabic test set show that monolingual models trained on translated data achieve the strongest performance, with further improvements from small-scale manual correction of training examples.

Transfer or Translate? Argument Mining in Arabic with No Native Annotations

While Knowledge Editing (KE) has been widely explored in English, its behavior in morphologically rich languages like Arabic remains underexamined. In this work, we present the first study of Arabic KE. We evaluate four methods (ROME, MEMIT, ICE, and LTE) on Arabic translations of the ZsRE and Counterfact benchmarks, analyzing both multilingual and cross-lingual settings. Our experiments on Llama-2-7B-chat show that parameter-based methods struggle with cross-lingual generalization, while instruction-tuned methods perform more robustly. We extend Learning-To-Edit (LTE) to a multilingual setting and show that joint Arabic-English training improves both editability and transfer. We release Arabic KE benchmarks and multilingual training for LTE data to support future research.

Downloads

Next from EMNLP 2025

ATHAR: A High-Quality and Diverse Dataset for Classical Arabic to English Translation

Similar lecture

Can Question Rewriting Help Conversational Question Answering?

Stay up to date with the latest Underline news!

PRODUCT

COMPANY

RESOURCES

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from EMNLP 2025

ATHAR: A High-Quality and Diverse Dataset for Classical Arabic to English Translation

Similar lecture

Can Question Rewriting Help Conversational Question Answering?

Stay up to date with the latest Underline news!

PRODUCT

COMPANY

RESOURCES

Downloads