---
title: "ArabIE: Joint Entity, Relation and Event Extraction for Arabic (2022)"
description: "The authors present ArabIE, a neural model that converts each sentence into a typed graph. 26 references, cited by 5 papers here."
authors: ["Niama El Khbir", "Nadi Tomeh", "Thierry Charnois"]
year: 2022
venue: "Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP)"
source: "https://aclanthology.org/2022.wanlp-1.31/"
doi: "10.18653/v1/2022.wanlp-1.31"
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/khbir-2022-arabie-joint-entity-relation-event/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/khbir-2022-arabie-joint-entity-relation-event/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2022](https://md.research.elamur.ai/free/en/papers/2022/page/6/) / ArabIE: Joint Entity, Relation and Event Extraction for Arabic

# ArabIE: Joint Entity, Relation and Event Extraction for Arabic

**Authors:** Niama El Khbir, [Nadi Tomeh](https://md.research.elamur.ai/free/en/authors/nadi-tomeh/) and [Thierry Charnois](https://md.research.elamur.ai/free/en/authors/thierry-charnois/) · **Year:** 2022 · **Venue:** [Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP)](https://md.research.elamur.ai/free/en/venues/wanlp/) ([WANLP 2022](https://md.research.elamur.ai/free/en/venues/wanlp/2022/)) · **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/2022.wanlp-1.31/) · [PDF](https://aclanthology.org/2022.wanlp-1.31.pdf) · [DOI 10.18653/v1/2022.wanlp-1.31](https://doi.org/10.18653/v1/2022.wanlp-1.31) · [OpenAlex](https://openalex.org/W4385574096)

**Citations:** 4 citations (OpenAlex, 2026-10-14) · [5](https://md.research.elamur.ai/free/en/papers/khbir-2022-arabie-joint-entity-relation-event/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Arabic information extraction research has mostly targeted named entity recognition. Relation and event extraction have received little attention, and no earlier system handled all three jointly. The authors present ArabIE, a neural model that converts each sentence into a typed graph. Nodes are entity and event-trigger spans, and edges are relations or event roles. The model follows the design of Lin et al. (2020). It encodes tokens with BERT, uses separate FFN+CRF BIO taggers for entities and triggers, scores node and edge types with FFNs, and decodes greedily. All tasks are trained together.

Arabic morphology complicates this, because a single word can contain several entities, for example a noun plus a possessive suffix. The paper compares three ways to handle this: morphological tokenization with CamelTools (tok_morph), WordPiece tokenization (tok_wp), and merging the labels of a word's sub-entities into one compound label (concat).

On the Arabic portion of ACE 2005, ArabIE sets the state of the art. Its scores are in the same range as joint systems for other languages. The authors conclude that morphological information matters for recognizing subword entities. This gives a baseline for an understudied area.

## Key points
- Data: Arabic ACE05 (LDC2006T06), with 403 files and about 100k words. It contains 32,438 entities, 4,719 relations, 2,270 triggers and 4,975 roles. There is no official split, so the authors use a random 80/10/10 split.
- Token encoding concatenates BERT's last and third-from-last layers. A span is represented by averaging its first and last token embeddings, and an edge by concatenating its two span vectors.
- Beam search with penalties for invalid graphs, as in Lin et al. (2020), did not beat plain greedy decoding.
- Sentence segmentation and token projection both lose some training annotations, and the paper quantifies this loss. Dev and test sets keep their full gold annotations in every setting. Time roles are excluded.
- Error analysis found that about 23.5% of event errors come from annotation problems. Among the other 35 event errors, 67% turn out to be missing gold labels for which the model's output agrees with the annotation guide.

## Interesting ideas
- Gold spans are mapped onto subword tokens through character-level alignment, with a majority-of-characters rule, and the number of annotations lost is reported for each tokenization scheme.
- A word holding several entities gets one compound label (e.g. PER-ORG), restricted to combinations seen in training, so no separate segmenter is needed.
- Entities and triggers have separate taggers, so a span can be both, such as a pronoun affix inside an event verb.
- Training data may be lossy after preprocessing, but evaluation always uses untouched gold dev/test data, so preprocessing losses stay visible in the scores.
- Errors are checked against the annotation guide's definitions, which revealed that many "false positives" are actually missing gold labels.

## For Mova

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

- **I1** (tokens): When English clitics or contractions ("John's", "can't") are split, the same alignment and projection could carry annotations over, and we could report how much each tokenizer variant loses.
- **I2** (tree): This could be a lightweight baseline for UD multiword tokens, letting us check whether explicit splitting actually beats a compound-label approach.
- **I3** (frames): Letting a predicate token also act as an argument anchor (e.g. imperative or pro-drop subjects) would keep who-did-what frames from discarding implicit participants.
- **I4** (learn): Silver-data experiments should be scored against unfiltered gold sets, so that agreement filtering cannot hide the cases it dropped.
- **I5** (learn): Mova's evaluation could include a step that sorts disagreements into guide-consistent omissions and real errors, which also helps when deriving repair rules.

*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

- [Centre National de la Recherche Scientifique](https://md.research.elamur.ai/free/en/labs/centre-national-de-la-recherche-scientifique/) — Research institute, Paris, France · 168 works · 62,369 citations
- [Laboratoire d'Informatique de Paris-Nord](https://md.research.elamur.ai/free/en/labs/laboratoire-d-informatique-de-paris-nord/) — Research institute, Villetaneuse, France · 9 works · 510 citations
- [Université Sorbonne Paris Nord](https://md.research.elamur.ai/free/en/universities/universite-sorbonne-paris-nord/) — University, Villetaneuse, France · 8 works · 468 citations

📚 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 (2): [Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/) · 2,908 works · [🔎 Information extraction](https://md.research.elamur.ai/free/en/topics/information-extraction/) · 167 works

## Cite

Cite as: Niama El Khbir, Nadi Tomeh and Thierry Charnois. 2022. ArabIE: Joint Entity, Relation and Event Extraction for Arabic. Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP).

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

```bibtex
@inproceedings{khbir2022arabie,
  title = {{ArabIE: Joint Entity, Relation and Event Extraction for Arabic}},
  author = {Niama {El Khbir}, Nadi Tomeh and Thierry Charnois},
  booktitle = {Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP)},
  year = {2022},
  doi = {10.18653/v1/2022.wanlp-1.31},
  url = {https://doi.org/10.18653/v1/2022.wanlp-1.31}
}
```

- [← previous When to Say What and How: Adapting the Elaborateness and Indirectness of Spoken Dialogue Systems](https://md.research.elamur.ai/free/en/papers/miehle-2022-when-say-what-how-adapting/)
- [next → ArNLI: Arabic Natural Language Inference for Entailment and Contradiction Detection](https://md.research.elamur.ai/free/en/papers/jallad-2022-arnli-arabic-natural-language-inference/)
- [↑ back to papers of 2022](https://md.research.elamur.ai/free/en/papers/2022/page/6/)

## References

26 references, 9 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Wasi Uddin Ahmad, Nanyun Peng, and Kai-Wei Chang. 2020. GATE: graph attention transformer encoder for cross-lingual relation and event extraction. CoRR, abs/2010.03009. [↗](https://arxiv.org/abs/2010.03009)
2. Mohammad AL-Smadi and Omar Qawasmeh. 2016. Knowledge-based approach for event extraction from arabic tweets. International Journal of Advanced Computer Science and Applications, 7(6). [↗](https://doi.org/10.14569/ijacsa.2016.070663)
3. Nasser Alsaedi and Pete Burnap. 2015. Arabic event detection in social media. In Computational Linguistics and Intelligent Text Processing, pages 384–401, Cham. Springer International Publishing. [find](https://scholar.google.com/scholar?q=Nasser+Alsaedi+and+Pete+Burnap%2E+2015%2E+Arabic+event+detection+in+social+media%2E+In+Computational+Linguistics+and+Intelligent+Text+Processing%2C+pages+384%E2%80%93401%2C+Cham%2E+Springer+International+Publishing%2E)
4. Wissam Antoun, Fady Baly, and Hazem Hajj. 2020. [AraBERT: Transformer-based model for Arabic language understanding](https://md.research.elamur.ai/free/en/papers/antoun-2020-arabert-transformer-based-model-arabic/). In Proceedings of the 4th Workshop on Open-Source Arabic Corpora and Processing Tools, with a Shared Task on Offensive Language Detection, pages 9–15, Marseille, France. European Language Resource Association. [↗](https://doi.org/10.48550/arxiv.2003.00104)
5. Yassine Benajiba, Mona Diab, and Paolo Rosso. 2008a. [Arabic named entity recognition using optimized feature sets](https://md.research.elamur.ai/free/en/papers/benajiba-2008-arabic-named-entity-recognition-optimized/). In Proceedings of the Conference on Empirical Methods in Natural Language Processing, EMNLP ’08, page 284–293, USA. Association for Computational Linguistics.
6. Yassine Benajiba, Mona Diab, and Paolo Rosso. 2009. Using language independent and language specific features to enhance arabic named entity recognition. Int. Arab J. Inf. Technol., 6:463–471. [find](https://scholar.google.com/scholar?q=Yassine+Benajiba%2C+Mona+Diab%2C+and+Paolo+Rosso%2E+2009%2E+Using+language+independent+and+language+specific+features+to+enhance+arabic+named+entity+recognition%2E+Int%2E+Arab+J%2E+Inf%2E+Technol%2E%2C+6%3A463%E2%80%93471%2E)
7. Yassine Benajiba, Mona T. Diab, and P. Rosso. 2008b. Arabic named entity recognition: An svm-based approach. [↗](https://doi.org/10.4995/thesis/10251/8318)
8. Yassine Benajiba, Imed Zitouni, Mona Diab, and Paolo Rosso. 2010. [Arabic named entity recognition: Using features extracted from noisy data](https://md.research.elamur.ai/free/en/papers/benajiba-2010-arabic-named-entity-recognition-features/). pages 281– 285. Tim Buckwalter. Arabic Morphological Analyzer Version 2.0 LDC2004L02.
9. Linguistic Data Consortium, 2004. [find](https://scholar.google.com/scholar?q=Linguistic+Data+Consortium%2C+2004%2E)
10. Nizar Y. Habash. 2010. Introduction to Arabic natural language processing, 1 edition, volume 3 of Synthesis Lectures on Human Language Technologies. Morgan and Claypool Publishers. [find](https://scholar.google.com/scholar?q=Nizar+Y%2E+Habash%2E+2010%2E+Introduction+to+Arabic+natural+language+processing%2C+1+edition%2C+volume+3+of+Synthesis+Lectures+on+Human+Language+Technologies%2E+Morgan+and+Claypool+Publishers%2E)
11. Chadi Helwe, Ghassan Dib, Mohsen Shamas, and Shady Elbassuoni. 2020. [A semi-supervised BERT approach for Arabic named entity recognition](https://md.research.elamur.ai/free/en/papers/helwe-2020-semi-supervised-bert-approach-arabic/). In Proceedings of the Fifth Arabic Natural Language Processing Workshop, pages 49–57, Barcelona, Spain (Online). Association for Computational Linguistics.
12. Ganesh Jawahar, Benoît Sagot, and Djamé Seddah. 2019. [What does BERT learn about the structure of language?](https://md.research.elamur.ai/free/en/papers/jawahar-2019-what-does-bert-learn-about/) In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3651–3657, Florence, Italy. Association for Computational Linguistics.
13. John D. Lafferty, Andrew McCallum, and Fernando C. N. Pereira. 2001. Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In Proceedings of the Eighteenth International Conference on Machine Learning, ICML ’01, pages 282–289, San Francisco, CA, USA. Morgan Kaufmann Publishers Inc. [find](https://scholar.google.com/scholar?q=John+D%2E+Lafferty%2C+Andrew+McCallum%2C+and+Fernando+C%2E+N%2E+Pereira%2E+2001%2E+Conditional+random+fields%3A+Probabilistic+models+for+segmenting+and+labeling+sequence+data%2E+In+Proceedings+of+the+Eighteenth+Interna)
14. Ying Lin, Heng Ji, Fei Huang, and Lingfei Wu. 2020. [A joint neural model for information extraction with global features](https://md.research.elamur.ai/free/en/papers/lin-2020-joint-neural-model-information-extraction/). In Proceedings of The 58th Annual Meeting of the Association for Computational Linguistics.
15. Reham Mohamed, Nagwa M. El-Makky, and Khaled Nagi. 2015. Arabrelat: Arabic relation extraction using distant supervision. In Proceedings of the International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management, IC3K 2015, page 410–417, Setubal, PRT. SCITEPRESS - Science and Technology Publications, Lda. [find](https://scholar.google.com/scholar?q=Reham+Mohamed%2C+Nagwa+M%2E+El%2DMakky%2C+and+Khaled+Nagi%2E+2015%2E+Arabrelat%3A+Arabic+relation+extraction+using+distant+supervision%2E+In+Proceedings+of+the+International+Joint+Conference+on+Knowledge+Discovery%2C+K)
16. Nazlia Naji. 2012. Arabic named entity recognition using artificial neural network. Journal of Computer Science, 8:1285–1293. [find](https://scholar.google.com/scholar?q=Nazlia+Naji%2E+2012%2E+Arabic+named+entity+recognition+using+artificial+neural+network%2E+Journal+of+Computer+Science%2C+8%3A1285%E2%80%931293%2E)
17. Trung Minh Nguyen and Thien Huu Nguyen. 2018. One for all: Neural joint modeling of entities and events. [↗](https://doi.org/10.48550/arxiv.1812.00195)
18. Ossama Obeid, Nasser Zalmout, Salam Khalifa, Dima Taji, Mai Oudah, Bashar Alhafni, Go Inoue, Fadhl Eryani, Alexander Erdmann, and Nizar Habash. 2020. [CAMeL tools: An open source python toolkit for Arabic natural language processing](https://md.research.elamur.ai/free/en/papers/obeid-2020-camel-tools-open-source-python/). In Proceedings of the 12th Language Resources and Evaluation Conference, pages 7022–7032, Marseille, France. European Language Resources Association.
19. Mai Oudah and Khaled Shaalan. 2012. [A pipeline Arabic named entity recognition using a hybrid approach](https://md.research.elamur.ai/free/en/papers/oudah-2012-pipeline-arabic-named-entity-recognition/). In Proceedings of COLING 2012, pages 2159–2176, Mumbai, India.
20. The COLING 2012 Organizing Committee. [find](https://scholar.google.com/scholar?q=The+COLING+2012+Organizing+Committee%2E)
21. Injy Sarhan, Yasser El-Sonbaty, and Mohamad Abou El-Nasr. 2016. Semi-supervised pattern based algorithm for arabic relation extraction. 2016 IEEE 28th International Conference on Tools with Artificial Intelligence (ICTAI), pages 177–183. [find](https://scholar.google.com/scholar?q=Injy+Sarhan%2C+Yasser+El%2DSonbaty%2C+and+Mohamad+Abou+El%2DNasr%2E+2016%2E+Semi%2Dsupervised+pattern+based+algorithm+for+arabic+relation+extraction%2E+2016+IEEE+28th+International+Conference+on+Tools+with+Artificial)
22. Nasrin Taghizadeh, Heshaam Faili, and Jalal Maleki. 2018. Cross-language learning for arabic relation extraction. Procedia Computer Science, 142:190– 197. [find](https://scholar.google.com/scholar?q=Nasrin+Taghizadeh%2C+Heshaam+Faili%2C+and+Jalal+Maleki%2E+2018%2E+Cross%2Dlanguage+learning+for+arabic+relation+extraction%2E+Procedia+Computer+Science%2C+142%3A190%E2%80%93+197%2E)
23. David Wadden, Ulme Wennberg, Yi Luan, and Hannaneh Hajishirzi. 2019. [Entity, relation, and event extraction with contextualized span representations](https://md.research.elamur.ai/free/en/papers/wadden-2019-entity-relation-event-extraction-contextualized/). In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 5784– 5789, Hong Kong, China. Association for Computational Linguistics.
24. C. Walker and Linguistic Data Consortium. 2005. ACE 2005 Multilingual Training Corpus. LDC corpora. Linguistic Data Consortium. [find](https://scholar.google.com/scholar?q=C%2E+Walker+and+Linguistic+Data+Consortium%2E+2005%2E+ACE+2005+Multilingual+Training+Corpus%2E+LDC+corpora%2E+Linguistic+Data+Consortium%2E)
25. Yonghui Wu, Mike Schuster, Zhifeng Chen, Quoc V. Le, Mohammad Norouzi, Wolfgang Macherey, Maxim Krikun, Yuan Cao, Qin Gao, Klaus Macherey, Jeff Klingner, Apurva Shah, Melvin Johnson, Xiaobing Liu, Lukasz Kaiser, Stephan Gouws, Yoshikiyo Kato, Taku Kudo, Hideto Kazawa, Keith Stevens, George Kurian, Nishant Patil, Wei Wang, Cliff Young, Jason Smith, Jason Riesa, Alex Rudnick, Oriol Vinyals, Greg Corrado, Macduff Hughes, and Jeffrey Dean. 2016. Google’s neural machine translation system: Bridging the gap between human and machine translation. CoRR, abs/1609.08144. [↗](https://arxiv.org/abs/1609.08144)
26. Tongtao Zhang, Heng Ji, and Avirup Sil. 2019. Joint Entity and Event Extraction with Generative Adversarial Imitation Learning. Data Intelligence, 1(2):99–120. [↗](https://doi.org/10.1162/dint_a_00014)

*Updated 1 November 2026*