---
title: "LowResContextQA at Qur'an QA 2023 Shared Task: Temporal"
description: "This paper describes a system for Task B of the Qur'an QA 2023 shared task. 23 references, cited by 3 papers here."
authors: ["Hariram Veeramani", "Surendrabikram Thapa", "Usman Naseem"]
year: 2023
venue: "Proceedings of ArabicNLP 2023"
source: "https://aclanthology.org/2023.arabicnlp-1.78/"
doi: "10.18653/v1/2023.arabicnlp-1.78"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/veeramani-2023-lowrescontextqa-qur-qa-2023-shared/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/veeramani-2023-lowrescontextqa-qur-qa-2023-shared/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2023](https://md.research.elamur.ai/free/en/papers/2023/page/12/) / LowResContextQA at Qur'an QA 2023 Shared Task: Temporal and Sequential Representation Augmented Question Answering Span Detection in Arabic

# LowResContextQA at Qur'an QA 2023 Shared Task: Temporal and Sequential Representation Augmented Question Answering Span Detection in Arabic

**Authors:** [Hariram Veeramani](https://md.research.elamur.ai/free/en/authors/hariram-veeramani/), [Surendrabikram Thapa](https://md.research.elamur.ai/free/en/authors/surendrabikram-thapa/) and [Usman Naseem](https://md.research.elamur.ai/free/en/authors/usman-naseem/) · **Year:** 2023 · **Venue:** [Proceedings of ArabicNLP 2023](https://md.research.elamur.ai/free/en/venues/arabicnlp/) ([ArabicNLP 2023](https://md.research.elamur.ai/free/en/venues/arabicnlp/2023/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2023.arabicnlp-1.78/) · [PDF](https://aclanthology.org/2023.arabicnlp-1.78.pdf) · [DOI 10.18653/v1/2023.arabicnlp-1.78](https://doi.org/10.18653/v1/2023.arabicnlp-1.78) · [OpenAlex](https://openalex.org/W4389518402)

**Citations:** 5 citations (OpenAlex, 2026-10-14) · [3](https://md.research.elamur.ai/free/en/papers/veeramani-2023-lowrescontextqa-qur-qa-2023-shared/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
This paper describes a system for Task B of the Qur'an QA 2023 shared task. The system receives a passage of consecutive Qur'anic verses and a question in Modern Standard Arabic. It must return up to ten ranked answer spans copied directly from the passage, or nothing when the passage contains no answer. The data is QRCD v1.2, and scoring uses partial Average Precision (pAP).

The authors use two extractive readers: the original AraELECTRA and an AraELECTRA fine-tuned on ArTyDiQA. They also try AraElectra-ARCD as a substitute for the first reader. From each reader they collect per-token start and end logits. A small decision module, either an MLP or an LSTM, then selects the best start-end pair. It works either on each reader's logits separately or on a fusion of both readers' logits.

Fusing logits through the MLP gave the best development scores, up to 0.442 pAP. However, the only test figure reported is 0.474, for the ArTyDiQA reader alone. The work suggests that lightweight late fusion of span scores can help in a small, specialised domain.

## Key points
- QRCD v1.2 contains 1,155 question-passage pairs and 1,399 question-passage-answer triplets, split roughly 70/10/20 into train, dev and test. About 15% of the questions have no answer.
- The pAP metric gives partial credit for partly overlapping and lower-ranked spans. A question with no answer earns full credit only if the system returns an empty result, and zero otherwise.
- The readers are AraELECTRA (Model 1), AraELECTRA fine-tuned on ArTyDiQA (Model 2) and AraElectra-ARCD (the Hugging Face checkpoint salti/AraElectra-base-finetuned-ARCD).
- Development pAP scores were:
  - Model 1: 0.367
  - Model 2: 0.406
  - Fused logits with the LSTM branch: 0.411
  - Fused logits with the MLP branch: 0.435
  - AraElectra-ARCD + AraELECTRA fused with the MLP: 0.442
- Model 2 scored 0.474 pAP on the test set. No test scores are given for the fused systems because the test set was unavailable to the authors. They name the small size of QRCD as a main limitation.

## Interesting ideas
- Instead of picking one reader, the boundary scores of two readers are merged and a tiny learned layer chooses the final span, which is a cheap ensemble that needs no retraining of the large models
- Abstention is a first-class outcome, because unanswerable questions are rewarded only when the system stays silent, so over-answering is directly penalised
- Ranked answers are graded with partial overlap rather than exact match, so a near-miss span still earns some credit and the ranking order matters
- Before facing a tiny specialised dataset, the reader is first adapted on a larger general QA set in the same language (ArTyDiQA), and this variant was the strongest single model

## For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

- **I1** (answer): Mova's tale and fable readers could combine span or entity candidates from several independent routes (tree-based, frame-based) with a small transparent scorer whose weights stay inspectable.
- **I2** (learn): evaluation suites could include deliberately unanswerable questions as negative controls, so a reader that invents answers loses points.
- **I3** (answer): school-test and QA scoring could adopt a pAP-style measure, separating "found roughly the right phrase" from "found nothing".
- **I4** (learn): when teaching a new domain with few gold examples, Mova could first train on broader silver QA data and then refine on the small in-domain set.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [University of California, Los Angeles](https://md.research.elamur.ai/free/en/universities/university-of-california-los-angeles/) — University, Los Angeles, United States · 87 works · 54,961 citations
- [Virginia Tech](https://md.research.elamur.ai/free/en/universities/virginia-tech/) — University, Blacksburg, United States · 36 works · 43,036 citations
- [James Cook University](https://md.research.elamur.ai/free/en/universities/james-cook-university/) — University, Townsville, Australia · 3 works · 23 citations

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,437 works

🧭 Topics (2): [Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/) · 2,908 works · [❓ Question answering](https://md.research.elamur.ai/free/en/topics/question-answering/) · 441 works

## Cite

Cite as: Hariram Veeramani, Surendrabikram Thapa and Usman Naseem. 2023. LowResContextQA at Qur'an QA 2023 Shared Task: Temporal and Sequential Representation Augmented Question Answering Span Detection in Arabic. Proceedings of ArabicNLP 2023.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{veeramani2023lowrescontextqa,
  title = {{LowResContextQA at Qur'an QA 2023 Shared Task: Temporal and Sequential Representation Augmented Question Answering Span Detection in Arabic}},
  author = {Hariram Veeramani, Surendrabikram Thapa and Usman Naseem},
  booktitle = {Proceedings of ArabicNLP 2023},
  year = {2023},
  doi = {10.18653/v1/2023.arabicnlp-1.78},
  url = {https://doi.org/10.18653/v1/2023.arabicnlp-1.78}
}
```

- [← previous Investigating Explicitation of Discourse Connectives in Translation using Automatic Annotations](https://md.research.elamur.ai/free/en/papers/yung-2023-investigating-explicitation-discourse-connectives-translation/)
- [next → Multi-Parallel Corpus of North Levantine Arabic](https://md.research.elamur.ai/free/en/papers/krubinski-2023-multi-parallel-corpus-north-levantine/)
- [↑ back to papers of 2023](https://md.research.elamur.ai/free/en/papers/2023/page/12/)

## References

23 references, 7 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Rasha Ahmed and ES Atwell. 2016. Developing an ontology of concepts in the qur’an. International Journal on Islamic Applications in Computer Science and Technology, 4(4):1–8. [find](https://scholar.google.com/scholar?q=Rasha+Ahmed+and+ES+Atwell%2E+2016%2E+Developing+an+ontology+of+concepts+in+the+qur%E2%80%99an%2E+International+Journal+on+Islamic+Applications+in+Computer+Science+and+Technology%2C+4%284%29%3A1%E2%80%938%2E)
2. Kevin Clark, Minh-Thang Luong, Quoc V Le, and Christopher D Manning. 2019. Electra: Pre-training text encoders as discriminators rather than generators. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Kevin+Clark%2C+Minh%2DThang+Luong%2C+Quoc+V+Le%2C+and+Christopher+D+Manning%2E+2019%2E+Electra%3A+Pre%2Dtraining+text+encoders+as+discriminators+rather+than+generators%2E+In+International+Conference+on+Learning+Represe)
3. Suchin Gururangan, Ana Marasović, Swabha Swayamdipta, Kyle Lo, Iz Beltagy, Doug Downey, and Noah A Smith. 2020. Don’t stop pretraining: Adapt language models to domains and tasks. arXiv preprint arXiv:2004.10964. [↗](https://arxiv.org/abs/2004.10964)
4. Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural computation, 9(8):1735– 1780. [↗](https://doi.org/10.1162/neco.1997.9.8.1735)
5. Rajaraman Kanagasabai, Saravanan Rajamanickam, Hariram Veeramani, Adam Westerski, and Kim Jung Jae. 2023. Semantists at ImageArg-2023: Exploring Cross-modal Contrastive and Ensemble Models for Multimodal Stance and Persuasiveness Classification. In Proceedings of the 10th Workshop on Argument Mining, Online and in Singapore. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Rajaraman+Kanagasabai%2C+Saravanan+Rajamanickam%2C+Hariram+Veeramani%2C+Adam+Westerski%2C+and+Kim+Jung+Jae%2E+2023%2E+Semantists+at+ImageArg%2D2023%3A+Exploring+Cross%2Dmodal+Contrastive+and+Ensemble+Models+for+Multimo)
6. Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. [Roberta: A robustly optimized bert pretraining approach](https://md.research.elamur.ai/free/en/papers/liu-2019-roberta-robustly-optimized-bert-pretraining/). arXiv preprint arXiv:1907.11692. [↗](https://arxiv.org/abs/1907.11692)
7. Rana Malhas and Tamer Elsayed. 2020. Ayatec: building a reusable verse-based test collection for arabic question answering on the holy qur’an. ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP), 19(6):1–21. [find](https://scholar.google.com/scholar?q=Rana+Malhas+and+Tamer+Elsayed%2E+2020%2E+Ayatec%3A+building+a+reusable+verse%2Dbased+test+collection+for+arabic+question+answering+on+the+holy+qur%E2%80%99an%2E+ACM+Transactions+on+Asian+and+Low%2DResource+Language+Infor)
8. Rana Malhas and Tamer Elsayed. 2022. Arabic machine reading comprehension on the holy qur’an using cl-arabert. Information Processing & Management, 59(6):103068. [↗](https://doi.org/10.1016/j.ipm.2022.103068)
9. Rana Malhas, Watheq Mansour, and Tamer Elsayed. 2022. [find](https://scholar.google.com/scholar?q=Rana+Malhas%2C+Watheq+Mansour%2C+and+Tamer+Elsayed%2E+2022%2E)
10. Qur’an QA 2022: [Overview of the first shared task on question answering over the holy qur’an](https://md.research.elamur.ai/free/en/papers/malhas-2022-qur-qa-2022-overview-first/). In Proceedinsg of the 5th Workshop on Open-Source Arabic Corpora and Processing Tools with Shared Tasks on Qur’an QA and Fine-Grained Hate Speech Detection, pages 79–87, Marseille, France. European Language Resources Association.
11. Wissam Antoun, Fady Baly, and Hazem Hajj. 2021. [AraELECTRA: Pre-training text discriminators for Arabic language understanding](https://md.research.elamur.ai/free/en/papers/antoun-2021-araelectra-pre-training-text-discriminators/). In Proceedings of the Sixth Arabic Natural Language Processing Workshop, pages 191–195, Kyiv, Ukraine (Virtual). Association for Computational Linguistics. [↗](https://doi.org/10.48550/arxiv.2012.15516)
12. Rana Malhas, Watheq Mansour, and Tamer Elsayed. 2023. [find](https://scholar.google.com/scholar?q=Rana+Malhas%2C+Watheq+Mansour%2C+and+Tamer+Elsayed%2E+2023%2E)
13. Qur’an QA 2023 [Shared Task: Overview of Passage Retrieval and Reading Comprehension Tasks over the Holy Qur’an](https://md.research.elamur.ai/free/en/papers/malhas-2023-qur-qa-2023-shared-task/). In Proceedings of the First Arabic Natural Language Processing Conference (ArabicNLP 2023), Singapore.
14. Muhammad Huzaifa Bashir, Aqil M Azmi, Haq Nawaz, Wajdi Zaghouani, Mona Diab, Ala Al-Fuqaha, and Junaid Qadir. 2023. Arabic natural language processing for qur’anic research: A systematic review. Artificial Intelligence Review, 56(7):6801–6854. [↗](https://doi.org/10.1007/s10462-022-10313-2)
15. Ensaf Hussein Mohamed and Wessam H El-Behaidy. 2021. An ensemble multi-label themes-based classification for holy qur’an verses using word2vec embedding. Arabian Journal for Science and Engineering, 46:3519–3529. [↗](https://doi.org/10.1007/s13369-020-05184-0)
16. Sara Rosenthal, Noura Farra, and Preslav Nakov. 2017. [SemEval-2017 task 4: Sentiment analysis in Twitter](https://md.research.elamur.ai/free/en/papers/rosenthal-2017-semeval-2017-task-4-sentiment/). In Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017), Vancouver, Canada. Association for Computational Linguistics.
17. Zineb Touati-Hamad, Mohamed Ridda Laouar, and Issam Bendib. 2020. Quran content representation in nlp. In Proceedings of the 10th International Conference on Information Systems and Technologies, pages 1–6. [find](https://scholar.google.com/scholar?q=Zineb+Touati%2DHamad%2C+Mohamed+Ridda+Laouar%2C+and+Issam+Bendib%2E+2020%2E+Quran+content+representation+in+nlp%2E+In+Proceedings+of+the+10th+International+Conference+on+Information+Systems+and+Technologies%2C+page)
18. Hariram Veeramani, Surendrabikram Thapa, and Usman Naseem. 2023a. Automated Citation Function Classification and Context Extraction in Astrophysics: Leveraging Paraphrasing and Question Answering. In Proceedings of the second Workshop on Information Extraction from Scientific Publications, Online. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Hariram+Veeramani%2C+Surendrabikram+Thapa%2C+and+Usman+Naseem%2E+2023a%2E+Automated+Citation+Function+Classification+and+Context+Extraction+in+Astrophysics%3A+Leveraging+Paraphrasing+and+Question+Answering%2E+In+)
19. Hariram Veeramani, Surendrabikram Thapa, and Usman Naseem. 2023b. [DialectNLU at NADI 2023 Shared Task: Transformer Based Multitask Approach Jointly Integrating Dialect and Machine Translation Tasks in Arabic](https://md.research.elamur.ai/free/en/papers/veeramani-2023-dialectnlu-nadi-2023-shared-task/). In Proceedings of The First Arabic Natural Language Processing Conference (ArabicNLP 2023), Singapore. Association for Computational Linguistics.
20. Hariram Veeramani, Surendrabikram Thapa, and Usman Naseem. 2023c. Enhancing ESG Impact Type Identification through Early Fusion and Multilingual Models. In Proceedings of the Sixth Workshop on Financial Technology and Natural Language Processing (FinNLP). Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Hariram+Veeramani%2C+Surendrabikram+Thapa%2C+and+Usman+Naseem%2E+2023c%2E+Enhancing+ESG+Impact+Type+Identification+through+Early+Fusion+and+Multilingual+Models%2E+In+Proceedings+of+the+Sixth+Workshop+on+Financi)
21. Hariram Veeramani, Surendrabikram Thapa, and Usman Naseem. 2023d. [KnowTellConvince at ArAIEval Shared Task: Disinformation and Persuasion Detection in Arabic using Similar and Contrastive Representation Alignment](https://md.research.elamur.ai/free/en/papers/veeramani-2023-knowtellconvince-araieval-shared-task-disinformation/). In Proceedings of The First Arabic Natural Language Processing Conference (ArabicNLP 2023), Singapore. Association for Computational Linguistics.
22. Hariram Veeramani, Surendrabikram Thapa, and Usman Naseem. 2023e. LowResourceNLU at BLP-2023 Task 1 2: Enhancing Sentiment Classification and Violence Incitement Detection in Bangla Through Aggregated Language Models. In Proceedings of the 1st International Workshop on Bangla Language Processing (BLP-2023), Singapore. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Hariram+Veeramani%2C+Surendrabikram+Thapa%2C+and+Usman+Naseem%2E+2023e%2E+LowResourceNLU+at+BLP%2D2023+Task+1+2%3A+Enhancing+Sentiment+Classification+and+Violence+Incitement+Detection+in+Bangla+Through+Aggregated)
23. Hariram Veeramani, Surendrabikram Thapa, and Usman Naseem. 2023f. Temporally Dynamic Session-Keyword Aware Sequential Recommendation system. In 2023 International Conference on Data Mining Workshops (ICDMW). [find](https://scholar.google.com/scholar?q=Hariram+Veeramani%2C+Surendrabikram+Thapa%2C+and+Usman+Naseem%2E+2023f%2E+Temporally+Dynamic+Session%2DKeyword+Aware+Sequential+Recommendation+system%2E+In+2023+International+Conference+on+Data+Mining+Workshops+%28)

*Updated 1 November 2026*