---
title: "Baleegh at KSAA-CAD 2024: Towards Enhancing Arabic"
description: "Arabic has far weaker reverse dictionary (RD) tools than English or Chinese. 13 references, cited by 2 papers here."
authors: ["Mais Alheraki", "Souham Meshoul"]
year: 2024
venue: "Proceedings of the Second Arabic Natural Language Processing Conference"
source: "https://aclanthology.org/2024.arabicnlp-1.78/"
doi: "10.18653/v1/2024.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/alheraki-2024-baleegh-ksaa-cad-2024-enhancing/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/alheraki-2024-baleegh-ksaa-cad-2024-enhancing/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2024](https://md.research.elamur.ai/free/en/papers/2024/page/12/) / Baleegh at KSAA-CAD 2024: Towards Enhancing Arabic Reverse Dictionaries

# Baleegh at KSAA-CAD 2024: Towards Enhancing Arabic Reverse Dictionaries

**Authors:** [Mais Alheraki](https://md.research.elamur.ai/free/en/authors/mais-alheraki/) and Souham Meshoul · **Year:** 2024 · **Venue:** [Proceedings of the Second Arabic Natural Language Processing Conference](https://md.research.elamur.ai/free/en/venues/arabicnlp/) ([ArabicNLP 2024](https://md.research.elamur.ai/free/en/venues/arabicnlp/2024/)) · **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/2024.arabicnlp-1.78/) · [PDF](https://aclanthology.org/2024.arabicnlp-1.78.pdf) · [DOI 10.18653/v1/2024.arabicnlp-1.78](https://doi.org/10.18653/v1/2024.arabicnlp-1.78) · [OpenAlex](https://openalex.org/W4402683874)

**Citations:** 1 citations (OpenAlex, 2026-10-14) · [2](https://md.research.elamur.ai/free/en/papers/alheraki-2024-baleegh-ksaa-cad-2024-enhancing/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Arabic has far weaker reverse dictionary (RD) tools than English or Chinese. An RD takes a description of a meaning and returns matching words. This paper is the Baleegh team's entry to the KSAA-CAD 2024 shared task, where each dictionary gloss must be mapped onto a target word embedding. The authors made two changes to the usual approach. First, they replaced the BERT-family encoders common in earlier Arabic RD work with AraT5 V2. Second, they added example contexts automatically to every training entry, pulled from Arabic Wikipedia through semantic vector search. The model encodes the input with AraT5, pools the result into one vector, and passes it through a linear layer that regresses onto three target spaces (electra, bertseg, bertmsa). The gloss-only model came close to the baselines on bertseg and bertmsa but was weaker on electra. The Wikipedia examples slightly reduced performance. The work matters as an early test of T5 for Arabic RD and as an honest negative result on retrieval-based data enrichment.

## Key points
- The KSAA-CAD dataset has 39,214 word–gloss entries split 31,372 / 3,921 / 3,922 (train/dev/test). Each entry has word, gloss and pos fields plus three target embeddings: electra, bertseg and bertmsa.
- Enrichment drew on Cohere's Arabic Wikipedia Embeddings (3.1M entries, embedded with multilingual-22-12). Each "word:gloss" string was embedded with that same model, and the top 5 passages by cosine similarity were kept, giving 156,860 examples.
- The model is the AraT5 V2 encoder (AraT5-base-1024), followed by mask-weighted mean pooling and a linear layer. It was trained with MSE loss, Adam at learning rate 3e-5, and only 2 epochs because longer training overfit.
- Gloss-only test cosine was 0.5678 for electra, 0.7168 for bertmsa and 0.7739 for bertseg. Adding examples lowered cosine and gave clearly worse rank scores. Rank was much worse than the CamelBERT and MARBERT baselines in all settings.
- The authors blame several factors: noisy or off-topic retrieved passages, words missing from Wikipedia, and targets built from definitions alone.

## Interesting ideas
- Use a single embedding model for both the query and the corpus, and phrase the query as "word:gloss" so the gloss pins down which sense of the word to retrieve contexts for; this cheaply turns a dictionary into a sense-tagged example bank.
- The enrichment failed partly because the training targets came only from definitions, so the added context worked against what the model was graded on; augmentation needs to match how the targets were built.
- The metrics told different stories: cosine scores were competitive while rank scores were much worse, so judging on one similarity measure would have been misleading.
- Regressing the same encoder onto several target spaces showed which spaces it fits easily (bertseg, bertmsa) and which it fits poorly (electra), which the authors link to how similar the vocabularies are.
- Treating a reverse dictionary as "description in, word out" is a direct model for choosing words from meaning.

## For Mova

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

- **I1** (world): Querying a corpus with lemma plus WordNet gloss could collect sense-specific example sentences for the ontology, which would help explain why a particular sense was chosen.
- **I2** (learn): Before adding auto-retrieved context to silver data, compare it against a no-augmentation control and check that the gold labels can actually reflect the extra signal.
- **I3** (learn): Report both closeness and ranking/retrieval metrics for any embedding-based component, so that a near-miss vector is not mistaken for picking the correct item.
- **I4** (tokens): Fitting our lemma representations to several external embedding spaces could serve as a probe of tokenizer and vocabulary compatibility before we pick one.
- **I5** (back): During generation, a frame's semantic description could be mapped to a ranked list of candidate lemmas, with the score for each recorded as an explanation of the lexical choice.

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

📚 Shelves (4): [🖥️ 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

🧭 Topics (1): [Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/) · 2,908 works

## Cite

Cite as: Mais Alheraki and Souham Meshoul. 2024. Baleegh at KSAA-CAD 2024: Towards Enhancing Arabic Reverse Dictionaries. Proceedings of the Second Arabic Natural Language Processing Conference.

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

```bibtex
@inproceedings{alheraki2024baleegh,
  title = {{Baleegh at KSAA-CAD 2024: Towards Enhancing Arabic Reverse Dictionaries}},
  author = {Mais Alheraki and Souham Meshoul},
  booktitle = {Proceedings of the Second Arabic Natural Language Processing Conference},
  year = {2024},
  doi = {10.18653/v1/2024.arabicnlp-1.78},
  url = {https://doi.org/10.18653/v1/2024.arabicnlp-1.78}
}
```

- [← previous ASOS at Arabic LLMs Hallucinations 2024: Can LLMs detect their Hallucinations :)](https://md.research.elamur.ai/free/en/papers/sibaee-2024-asos-arabic-llms-hallucinations-2024/)
- [next → Bangor University at WojoodNER 2024: Advancing Arabic Named Entity Recognition with CAMeLBERT-Mix](https://md.research.elamur.ai/free/en/papers/alshammari-2024-bangor-university-wojoodner-2024-advancing/)
- [↑ back to papers of 2024](https://md.research.elamur.ai/free/en/papers/2024/page/12/)

## References

13 references, 6 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Rawan Al-Matham, Waad Alshammari, Abdulrahman AlOsaimy, Sarah Alhumoud, Asma Wazrah, Afrah Altamimi, Halah Alharbi, and Abdullah Alaifi. 2023. [Ksaa-rd shared task: Arabic reverse dictionary](https://md.research.elamur.ai/free/en/papers/matham-2023-ksaa-rd-shared-task-arabic/). pages 450–460. Association for Computational Linguistics.
2. Waad Alshammari, Amal Almazrua, Asma Al Wazrah, Rawan Almatham, Muneera Alhoshan, Abdulrahman AlOsaimy, and Alfaifi Abdullah Altamimi, Afrah and. 2024. KSAA-CAD: Contemporary Arabic dictionary shared task. In Proceedings of the 2nd Arabic Natural Language Processing Conference (Arabic-NLP), Part of the ACL 2024. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Waad+Alshammari%2C+Amal+Almazrua%2C+Asma+Al+Wazrah%2C+Rawan+Almatham%2C+Muneera+Alhoshan%2C+Abdulrahman+AlOsaimy%2C+and+Alfaifi+Abdullah+Altamimi%2C+Afrah+and%2E+2024%2E+KSAA%2DCAD%3A+Contemporary+Arabic+dictionary+shared+)
3. Linting Xue, Noah Constant, Adam Roberts, Mihir Kale, Rami Al-Rfou, Aditya Siddhant, Aditya Barua, and Colin Raffel. 2021. [mt5: A massively multilingual pre-trained text-to-text transformer](https://md.research.elamur.ai/free/en/papers/xue-2021-mt5-massively-multilingual-pre-trained/). pages 483–498. Association for Computational Linguistics.
4. Alfonso Ardoiz, Miguel Ortega-Martin, Óscar Garcia-Sierra, Jorge Álvarez, Ignacio Arranz, and Adrián Alonso. 2022. Mmg at semeval-2022 task 1: A reverse dictionary approach based on a review of the dataset from a lexicographic perspective. pages 68– 74. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Alfonso+Ardoiz%2C+Miguel+Ortega%2DMartin%2C+%C3%93scar+Garcia%2DSierra%2C+Jorge+%C3%81lvarez%2C+Ignacio+Arranz%2C+and+Adri%C3%A1n+Alonso%2E+2022%2E+Mmg+at+semeval%2D2022+task+1%3A+A+reverse+dictionary+approach+based+on+a+review+of+the+da)
5. Pinzhen Chen and Zheng Zhao. 2022. A unified model for reverse dictionary and definition modelling. pages 8–13. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Pinzhen+Chen+and+Zheng+Zhao%2E+2022%2E+A+unified+model+for+reverse+dictionary+and+definition+modelling%2E+pages+8%E2%80%9313%2E+Association+for+Computational+Linguistics%2E)
6. Ahmed Elbakry, Mohamed Gabr, Muhammad El-Nokrashy, and Badr AlKhamissi. 2023. [Rosetta stone at ksaa-rd shared task: A hop from language modeling to word–definition alignment](https://md.research.elamur.ai/free/en/papers/elbakry-2023-rosetta-stone-ksaa-rd-shared/). pages 477–482. Association for Computational Linguistics.
7. Ehsan Kamalloo, Xinyu Zhang, Odunayo Ogundepo, Nandan Thakur, David Alfonso-Hermelo, Mehdi Rezagholizadeh, and Jimmy Lin. 2023. Evaluating embedding apis for information retrieval. [↗](https://doi.org/10.48550/arxiv.2305.06300)
8. Anne Stallman Kilian, William E. Nagy, P. David Pearson, Richard C. Anderson, and Georgia Earnest Garcia. 1995. Learning vocabulary from context: effects of focusing attention on individual words during reading. [find](https://scholar.google.com/scholar?q=Anne+Stallman+Kilian%2C+William+E%2E+Nagy%2C+P%2E+David+Pearson%2C+Richard+C%2E+Anderson%2C+and+Georgia+Earnest+Garcia%2E+1995%2E+Learning+vocabulary+from+context%3A+effects+of+focusing+attention+on+individual+words+duri)
9. Sunil B Mane, Harshal Navneet Patil, Kanhaiya Balaji Madaswar, and Pranav Nitin Sadavarte. 2022. Wordalchemy: A transformer-based reverse dictionary. pages 1–5. [find](https://scholar.google.com/scholar?q=Sunil+B+Mane%2C+Harshal+Navneet+Patil%2C+Kanhaiya+Balaji+Madaswar%2C+and+Pranav+Nitin+Sadavarte%2E+2022%2E+Wordalchemy%3A+A+transformer%2Dbased+reverse+dictionary%2E+pages+1%E2%80%935%2E)
10. El Moatez Billah Nagoudi, AbdelRahim Elmadany, and Muhammad Abdul-Mageed. 2021. [Arat5: Text-to-text transformers for arabic language generation](https://md.research.elamur.ai/free/en/papers/nagoudi-2022-arat5-text-text-transformers-arabic/).
11. Abdelrahim Qaddoumi. 2023. [Abed at ksaa-rd shared task: Enhancing arabic word embedding with modified bert multilingual](https://md.research.elamur.ai/free/en/papers/qaddoumi-2023-abed-ksaa-rd-shared-task/). pages 472–476. Association for Computational Linguistics.
12. Fanchao Qi, Lei Zhang, Yanhui Yang, Zhiyuan Liu, and Maosong Sun. 2020. Wantwords: An open-source online reverse dictionary system. pages 175–181. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Fanchao+Qi%2C+Lei+Zhang%2C+Yanhui+Yang%2C+Zhiyuan+Liu%2C+and+Maosong+Sun%2E+2020%2E+Wantwords%3A+An+open%2Dsource+online+reverse+dictionary+system%2E+pages+175%E2%80%93181%2E+Association+for+Computational+Linguistics%2E)
13. Serry Sibaee, Samar Ahmad, Ibrahim Khurfan, Vian Sabeeh, Ahmed Bahaaulddin, Hanan Belhaj, and Abdullah Alharbi. 2023. [Qamosy at arabic reverse dictionary shared task: Semi decoder architecture for reverse dictionary with sbert encoder](https://md.research.elamur.ai/free/en/papers/sibaee-2023-qamosy-arabic-reverse-dictionary-shared/). pages 467– 471. Association for Computational Linguistics.

*Updated 1 November 2026*