Advancements and challenges in Arabic question answering systems: a comprehensive survey
DOI:
https://doi.org/10.38152/bjtv7n4-028Abstract
This paper explores the development and challenges of Arabic Question Answering Systems (QAS), with a particular focus on addressing the linguistic nuances and data scarcity unique to Arabic. It categorizes Arabic QAS by domain (open or closed), question type (factoid, causal, complex), and modeling approach (rule-based, machine learning, deep learning). Key recent systems are reviewed, including their methodologies, datasets, and performance metrics, highlighting the growing role of deep learning techniques. State-of-the-art NLP methods, especially transformers, have greatly advanced QAS, although these gains are more substantial for English. Despite recent progress, Arabic QAS research remains limited by resource constraints, including a reliance on translated datasets and the absence of comprehensive Arabic benchmarks.
References
ABDALLAH, A.; KASEM, M.; ABDALLA, M.; MAHMOUD, M. et al. ArabicaQA: A Comprehensive Dataset for Arabic Question Answering. In: Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2024, Washington DC, USA. Association for Computing Machinery, p. 2049–2059. DOI: 10.1145/3626772.3657889. Disponível em: https://doi.org/10.1145/3626772.3657889.
ABOUENOUR, L.; BOUZOUBA, K.; ROSSO, P. An evaluated semantic query expansion and structure-based approach for enhancing Arabic question/answering. International Journal on Information and Communication Technologies, 3, n. 3, p. 37-51, 2010.
AHMED, W.; PV, A. Web-Based Arabic Question Answering System using Machine Learning Approach. International Journal of Advanced Research in Computer Science, 8, n. 1, 2017.
AL-OMARI, H.; DUWAIRI, R. So2al-wa-Gwab: A New Arabic Question-Answering Dataset Trained on Answer Extraction Models. ACM Trans. Asian Low-Resour. Lang. Inf. Process., 22, n. 8, p. Article 205, 2023.
AL-SHENAK, M.; NAHAR, K.; HALAWANI, K. M. H. Aqas: Arabic question answering system based on svm, svd, and lsi. Journal of Theoretical and Applied Information Technology, 97, n. 2, p. 681-691, 2019.
ALAMI, H.; EL MAHDAOUY, A.; BENLAHBIB, A.; EN-NAHNAHI, N. et al. DAQAS: Deep Arabic Question Answering System based on duplicate question detection and machine reading comprehension. Journal of King Saud University - Computer and Information Sciences, 35, n. 8, p. 101709, 2023/09/01/ 2023.
ALASMARI, A.; ALHUMOUD, S.; ALSHAMMARI, W., 2024, Torino, Italia. AraMed: Arabic Medical Question Answering using Pretrained Transformer Language Models. ELRA and ICCL. 50-56. Disponível em: https://aclanthology.org/2024.osact-1.6.
ALBARGHOTHI, A.; KHATER, F.; SHAALAN, K. Arabic Question Answering Using Ontology. Procedia Computer Science, 117, p. 183-191, 2017/01/01/ 2017.
ALKHURAYYIF, Y.; SAIT, A. R. W. Developing an Open Domain Arabic Question Answering System Using a Deep Learning Technique. IEEE Access, 11, p. 69131-69143, 2023.
ALRAYZAH, A.; ALSOLAMI, F.; SALEH, M. Challenges and opportunities for Arabic question-answering systems: current techniques and future directions. PeerJ Computer Science, 9, p. e1633, 2023.
ALSALEH, A.; ALTHABITI, S.; ALSHAMMARI, I.; ALNEFAIE, S. et al., 2022, Marseille, France. LK2022 at Qur’an QA 2022: simple transformers model for finding answers to questions from Qur’an. European Language Resources Association. 120-125. Disponível em: https://aclanthology.org/volumes/2022.osact-1/.
ALSUBHI, K.; JAMAL, A.; ALHOTHALI, A. Deep learning-based approach for Arabic open domain question answering. PeerJ Computer Science, 8, p. e952, 2022.
ANTOUN, W.; BALY, F.; HAJJ, H., 2021, Kyiv, Ukraine (Virtual). AraELECTRA: Pre-Training Text Discriminators for Arabic Language Understanding. Association for Computational Linguistics. Disponível em: https://aclanthology.org/2021.wanlp-1.20.
ARTETXE, M.; RUDER, S.; YOGATAMA, D., 2019, Online. On the Cross-lingual Transferability of Monolingual Representations. 4623-4637.
ATEF, A.; MATTAR, B.; SHERIF, S.; ELREFAI, E. et al., 2020, AQAD: 17,000+ Arabic Questions for Machine Comprehension of Text. 1-6.
AZMI, A.; ALWANEEN, T. A deep learning model for answering why-questions in Arabic. Indonesian Journal of Computer Science, 12, n. 2, p. 401-409, 2023.
AZMI, A. M.; ALSHENAIFI, N. A. Lemaza: An Arabic why-question answering system. Natural Language Engineering, 23, n. 6, p. 877-903, 2017.
BILTAWI, M. M.; TEDMORI, S.; AWAJAN, A. Arabic Question Answering Systems: Gap Analysis. IEEE Access, 9, p. 63876-63904, 2021.
BOUZIANE, A.; BOUCHIHA, D.; DOUMI, N.; MALKI, M. Toward an arabic question answering system over linked data. Jordanian Journal of Computers and Information Technology (JJCIT), 4, n. 2, p. 102-115, 2018.
CLARK, J. H.; CHOI, E.; COLLINS, M.; GARRETTE, D. et al. Tydi qa: A benchmark for information-seeking question answering in ty pologically di verse languages. Transactions of the Association for Computational Linguistics, 8, p. 454-470, 2020.
DIEFENBACH, D.; TANON, T., PELLISSIER; SINGH, K.; MARET, P. Question Answering Benchmarks for Wikidata. In: ISWC 2017, 2017, Vienne, Austria. Disponível em: https://hal.science/hal-01637141.
ELSAYED, K. N. An Arabic Natural Language Interface System for a Database of the Holy Quran. International Journal of Advanced Research in Artificial Intelligence, 4, n. 7, 2015.
HANANE, B.; MACHKOUR, M.; KOUTTI, L. A model of a generic Arabic language interface for multimodel database. International Journal of Speech Technology, 23, n. 3, p. 669-681, 2020/09/01 2020.
INDURKHYA, N.; DAMERAU, F. J. Handbook of natural language processing. Chapman and Hall/CRC, 2010. 0429149204.
ISMAIL, W. S.; HOMSI, M. N. DAWQAS: A Dataset for Arabic Why Question Answering System. Procedia Comput. Sci., 142, n. C, p. 123–131, 2018.
KOLOMIYETS, O.; MOENS, M.-F. A survey on question answering technology from an information retrieval perspective. Information Sciences, 181, n. 24, p. 5412-5434, 2011/12/15/ 2011.
KORABLINOV, V.; BRASLAVSKI, P. RuBQ: A Russian Dataset for Question Answering over Wikidata. In: The Semantic Web – ISWC 2020: 19th International Semantic Web Conference, Athens, Greece, November 2–6, 2020, Proceedings, Part II, 2020, Athens, Greece. Springer-Verlag, p. 97–110. DOI: 10.1007/978-3-030-62466-8_7. Disponível em: https://doi.org/10.1007/978-3-030-62466-8_7.
LAHBARI, I.; ALAOUI, S. O. E.; ZIDANI, K. A. Toward a new arabic question answering system. International Arab Journal of Information Technology, 15, p. 610-619, 2018.
LEWIS, P.; OĞUZ, B.; RINOTT, R.; RIEDEL, S. et al., 2020, Online. MLQA: Evaluating cross-lingual extractive question answering. Association for Computational Linguistics. 7315–7330. Disponível em: https://aclanthology.org/2020.acl-main.653/.
MALHAS, R.; ELSAYED, T. AyaTEC: Building a Reusable Verse-Based Test Collection for Arabic Question Answering on the Holy Qur’an. ACM Trans. Asian Low-Resour. Lang. Inf. Process., 19, n. 6, p. Article 78, 2020.
MALHAS, R.; ELSAYED, T. Arabic machine reading comprehension on the Holy Qur’an using CL-AraBERT. Information Processing & Management, 59, n. 6, p. 103068, 2022/11/01/ 2022.
MISHRA, A.; JAIN, S. K. A survey on question answering systems with classification. Journal of King Saud University - Computer and Information Sciences, 28, n. 3, p. 345-361, 2016/07/01/ 2016.
MOZANNAR, H.; HAJAL, K. E.; MAAMARY, E.; HAJJ, H., 2019, Florence, Italy. Neural Arabic question answering. Association for Computational Linguistics. 108–118. Disponível em: https://aclanthology.org/W19-4612.
NABIL, M.; ABDELMEGIED, A.; AYMAN, Y.; FATHY, A. et al., 2017, AlQuAnS - An Arabic Language Question Answering System.
PANDYA, H. A.; BHATT, B. S. Question Answering Survey: Directions, Challenges, Datasets. Evaluation Matrices. arXiv, 2021.
PETERS, M. E.; NEUMANN, M.; IYYER, M.; GARDNER, M. et al., 2018, New Orleans, Louisiana. Deep Contextualized Word Representations. 2227-2237. Disponível em: https://aclanthology.org/N18-1202.
PURWARIANTI, A.; TSUCHIYA, M.; NAKAGAWA, S. A machine learning approach for Indonesian question answering system. In: Proceedings of the 25th conference on Proceedings of the 25th IASTED International Multi-Conference: artificial intelligence and applications, 2007, Innsbruck, Austria. ACTA Press, p. 537–542.
RAJPURKAR, P.; ZHANG, J.; LOPYREV, K.; LIANG, P., 2016, Austin, Texas. Squad: 100,000+ questions for machine comprehension of text. Association for Computational Linguistics. 2383–2392. Disponível em: https://aclanthology.org/D16-1264.
SAMMOUDI, M.; HABAYBEH, A.; ASHQAR, H. I.; ELHENAWY, M. Question-Answering (QA) Model for a Personalized Learning Assistant for Arabic Language. arXiv preprint arXiv:2406.08519, 2024.
SAMY, H.; HASSANEIN, E. E.; SHAALAN, K. Arabic question answering: a study on challenges, systems, and techniques. International Journal of Computer Applications, 975, p. 8887, 2019.
SARHAN, A. A proposed architecture for dynamically built NLIDB systems. Int. J. Know.-Based Intell. Eng. Syst., 13, n. 2, p. 59–70, 2009.
SHARMA, Y.; GUPTA, S. Deep Learning Approaches for Question Answering System. Procedia Computer Science, 132, p. 785-794, 2018/01/01/ 2018.
SIDHOUM, A. H.; MATAOUI, M. H.; SEBBAK, F.; SMAÏLI, K., 2022, English, Boumerdès, Algeria. ACQAD: A Dataset for Arabic Complex Question Answering. https://hal.science/hal-03992129v1/document
https://hal.science/hal-03992129v1/file/ICCSAITCS_2022_paper_9032.pdf. Disponível em: https://hal.science/hal-03992129.
SLEEM, A.; LOTFY ELREFAI, E. M.; MATAR, M. M.; NAWAZ, H., 2022, Marseille, France. Stars at qur’an qa 2022: Building automatic extractive question answering systems for the holy qur’an with transformer models and releasing a new dataset. European Language Resources Association. 146-153.
STAŠ, J.; HLÁDEK, D.; KOCTÚR, T. Slovak Question Answering Dataset Based on the Machine Translation of the Squad V2.0. Journal of Linguistics/Jazykovedný casopis, 74, n. 1, p. 381-390, 2023.
