---
title: "Dialectal Arabic to English Machine Translation: Pivoting through"
description: "Salloum and Habash build ELISSA, a largely rule-based DA-to-MSA translator that serves as a front… 35 references, cited by 31 papers here."
authors: ["Wael Salloum", "Nizar Habash"]
year: 2013
venue: "Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies"
source: "https://aclanthology.org/N13-1036/"
licence: "CC BY-NC-SA 3.0 (ACL Anthology, before 2016)"
licence_url: "https://creativecommons.org/licenses/by-nc-sa/3.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/salloum-2013-dialectal-arabic-english-machine-translation/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/salloum-2013-dialectal-arabic-english-machine-translation/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2013](https://md.research.elamur.ai/free/en/papers/2013/page/2/) / Dialectal Arabic to English Machine Translation: Pivoting through Modern Standard Arabic

# Dialectal Arabic to English Machine Translation: Pivoting through Modern Standard Arabic

**Authors:** [Wael Salloum](https://md.research.elamur.ai/free/en/authors/wael-salloum/) and [Nizar Habash](https://md.research.elamur.ai/free/en/authors/nizar-habash/) · **Year:** 2013 · **Venue:** [Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies](https://md.research.elamur.ai/free/en/venues/naacl/) ([NAACL 2013](https://md.research.elamur.ai/free/en/venues/naacl/2013/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY-NC-SA 3.0 (ACL Anthology, before 2016)](https://creativecommons.org/licenses/by-nc-sa/3.0/)

**Links:** [Publisher's page](https://aclanthology.org/N13-1036/) · [PDF](https://aclanthology.org/N13-1036.pdf) · [OpenAlex](https://openalex.org/W2164503643)

**Citations:** 37 citations (OpenAlex, 2026-10-14) · [31](https://md.research.elamur.ai/free/en/papers/salloum-2013-dialectal-arabic-english-machine-translation/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Dialectal Arabic (DA) has no standard spelling and very few tools or parallel corpora. Modern Standard Arabic (MSA), by contrast, is well resourced, so MSA-trained translation systems often treat dialect words as unknown names. Salloum and Habash build ELISSA, a largely rule-based DA-to-MSA translator that serves as a front end for existing MSA tools. Working on raw, untokenized text, it first finds dialectal words and multi-word constructions. The signals it uses include being out of vocabulary, being analysed by the dialect morphological analyzer ADAM, appearing in DA-MSA dictionaries, and being rare. Hand-written transfer rules then rewrite the chosen spans at the level of features, lemmas and surface forms. This produces a lattice of MSA candidates, which an MSA language model ranks. The chosen MSA text goes to an MSA-English SMT system. On three blind test sets, BLEU improves by 0.61 to 1.41 absolute points, and manual checking finds about 93% of rewritten tokens are correct MSA. The study shows that pivoting through a richer sister variety is a cheap complement to collecting dialect parallel data.

## Key points
- ELISSA accepts only untokenized input and has three output modes: a top-1 sentence, an n-best list, or a map file linking source words or phrases to MSA phrases. Ranking uses an untokenized MSA language model.
- The best selection setting works at the phrase level. It takes the union of OOV, ADAM-analysable and DICT words, then removes words with training frequency ≥ 50. This setting beat OOV-only selection, and the top system on dev was also the top system on every test set.
- BLEU gains over the baseline:
  - speech-test (multi-dialect: Iraqi, Levantine, Gulf, Egyptian): 38.18 → 39.13, +0.95, 2.5% relative;
  - web-lev-test: 9.13 → 10.54, +1.41, 15.4% relative;
  - web-egy-test: 18.98 → 19.59, +0.61, 3.2% relative.
- Manual analysis covered 300 of 708 affected dev sentences. Of 482 handled tokens, 449 (93.15%) received good MSA. Errors came mostly from misspellings, proper nouns and disfluent speech input.
- The authors contrast their work with Zbib et al. (2012), whose oracle human MSA pivot reduced OOV from 2.27% to 0.98%. Yet adding 1.5M words of DA-English data helped BLEU more (+6.81 vs +4.91), which suggests domain mismatch matters more than vocabulary coverage alone.

## Interesting ideas
- Rare words that do appear in training, but only in narrow contexts, behave like unknown words, so the system rewrites them too instead of only true OOVs.
- Rules generate every plausible normalization, for example demonstrative variants differing in gender, number and rationality, and a separate scorer picks the one that fits agreement in context.
- The rewriter can emit a map file from source spans to their paraphrases, so downstream tools work on standardized text while results stay traceable to the original words.
- Error analysis is restricted to sampled tokens the system actually changed, and errors are sorted by cause (spelling, names, disfluency).
- Before building anything, the authors run an oracle check: a human-made pivot sent through an off-the-shelf system, to see whether pivoting can pay off at all.

## For Mova

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

- **I1** (tokens): flag low-frequency forms seen in few contexts as "near-unknown" and send them through full morphological analysis rather than trusting a memorised tag.
- **I2** (tokens): normalize informal English (gonna, ain't, dialect spellings) into several standard candidates and choose by agreement checks, logging which rule produced the winner.
- **I3** (tree): parse a standardized version of nonstandard input, then use the span map to project the UD tree back onto the original tokens, keeping each step explainable.
- **I4** (learn): evaluate each self-induced repair rule only on the tokens it touches, with a cause breakdown, so harmful rules are spotted without noise from untouched text.
- **I5** (back): before building translation through the meta-world, hand-build gold graphs for a few sentences and regenerate text from them to measure the ceiling of the approach.

*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

- [Columbia University](https://md.research.elamur.ai/free/en/universities/columbia-university/) — University, New York, United States · 241 works · 54,053 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): [🔁 Machine translation](https://md.research.elamur.ai/free/en/topics/machine-translation/) · 1,087 works · [Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/) · 2,908 works

## Cite

Cite as: Wael Salloum and Nizar Habash. 2013. Dialectal Arabic to English Machine Translation: Pivoting through Modern Standard Arabic. Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.

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

```bibtex
@inproceedings{salloum2013dialectal,
  title = {{Dialectal Arabic to English Machine Translation: Pivoting through Modern Standard Arabic}},
  author = {Wael Salloum and Nizar Habash},
  booktitle = {Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
  year = {2013},
  url = {https://aclanthology.org/N13-1036/}
}
```

- [← previous Classifying English Documents by National Dialect](https://md.research.elamur.ai/free/en/papers/lui-2013-classifying-english-documents-national-dialect/)
- [next → Leveraging Synthetic Discourse Data via Multi-task Learning for Implicit Discourse Relation Recognition](https://md.research.elamur.ai/free/en/papers/lan-2013-leveraging-synthetic-discourse-data-multi/)
- [↑ back to papers of 2013](https://md.research.elamur.ai/free/en/papers/2013/page/2/)

## References

35 references, 16 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Hitham Abo Bakr, Khaled Shaalan, and Ibrahim Ziedan. 2008. A Hybrid Approach for Converting Written Egyptian Colloquial Dialect into Diacritized Arabic. In The 6th International Conference on Informatics and Systems, INFOS2008. Cairo University. [find](https://scholar.google.com/scholar?q=Hitham+Abo+Bakr%2C+Khaled+Shaalan%2C+and+Ibrahim+Ziedan%2E+2008%2E+A+Hybrid+Approach+for+Converting+Written+Egyptian+Colloquial+Dialect+into+Diacritized+Arabic%2E+In+The+6th+International+Conference+on+Informat)
2. Rania Al-Sabbagh and Roxana Girju. 2010. [Mining the Web for the Induction of a Dialectical Arabic Lexicon](https://md.research.elamur.ai/free/en/papers/sabbagh-2010-mining-web-induction-dialectical-arabic/). In Nicoletta Calzolari, Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odijk, Stelios Piperidis, Mike Rosner, and Daniel Tapias, editors, LREC. European Language Resources Association.
3. Sarah Alkuhlani and Nizar Habash. 2011. [A Corpus for Modeling Morpho-Syntactic Agreement in Arabic: Gender, Number and Rationality](https://md.research.elamur.ai/free/en/papers/alkuhlani-2011-corpus-modeling-morpho-syntactic-agreement/). In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics (ACL’11), Portland, Oregon, USA.
4. Chris Callison-Burch, Philipp Koehn, and Miles Osborne. 2006. Improved statistical machine translation using paraphrases. In Proceedings of the Human Language Technology Conference of the NAACL, Main Conference, pages 17–24. [find](https://scholar.google.com/scholar?q=Chris+Callison%2DBurch%2C+Philipp+Koehn%2C+and+Miles+Osborne%2E+2006%2E+Improved+statistical+machine+translation+using+paraphrases%2E+In+Proceedings+of+the+Human+Language+Technology+Conference+of+the+NAACL%2C+Main+)
5. David Chiang, Mona Diab, Nizar Habash, Owen Rambow, and Safiullah Shareef. 2006. [Parsing Arabic Dialects](https://md.research.elamur.ai/free/en/papers/chiang-2006-parsing-arabic-dialects/). In Proceedings of the European Chapter of ACL (EACL). [↗](https://doi.org/10.7916/d85t3tzg)
6. Mona Diab, Kadri Hacioglu, and Daniel Jurafsky. 2007. Automated Methods for Processing Arabic Text: From Tokenization to Base Phrase Chunking. In Antal van den Bosch and Abdelhadi Soudi, editors, Arabic Computational Morphology: Knowledge-based and Empirical Methods. Kluwer/Springer. [find](https://scholar.google.com/scholar?q=Mona+Diab%2C+Kadri+Hacioglu%2C+and+Daniel+Jurafsky%2E+2007%2E+Automated+Methods+for+Processing+Arabic+Text%3A+From+Tokenization+to+Base+Phrase+Chunking%2E+In+Antal+van+den+Bosch+and+Abdelhadi+Soudi%2C+editors%2C+Arab)
7. Jinhua Du, Jie Jiang, and Andy Way. 2010. Facilitating translation using source language paraphrase lattices. In Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, EMNLP’10, pages 420–429, Cambridge, Massachusetts. [find](https://scholar.google.com/scholar?q=Jinhua+Du%2C+Jie+Jiang%2C+and+Andy+Way%2E+2010%2E+Facilitating+translation+using+source+language+paraphrase+lattices%2E+In+Proceedings+of+the+2010+Conference+on+Empirical+Methods+in+Natural+Language+Processing%2C)
8. Kevin Duh and Katrin Kirchhoff. 2005. [POS tagging of dialectal Arabic: a minimally supervised approach](https://md.research.elamur.ai/free/en/papers/duh-2005-pos-tagging-dialectal-arabic-minimally/). In Proceedings of the ACL Workshop on Computational Approaches to Semitic Languages, Semitic ’05, pages 55–62, Ann Arbor, Michigan.
9. David Graff and Christopher Cieri. 2003. English Gigaword, LDC Catalog No.: LDC2003T05. Linguistic Data Consortium, University of Pennsylvania. [find](https://scholar.google.com/scholar?q=David+Graff+and+Christopher+Cieri%2E+2003%2E+English+Gigaword%2C+LDC+Catalog+No%2E%3A+LDC2003T05%2E+Linguistic+Data+Consortium%2C+University+of+Pennsylvania%2E)
10. Nizar Habash and Owen Rambow. 2005. [Arabic Tokenization, Part-of-Speech Tagging and Morphological Disambiguation in One Fell Swoop](https://md.research.elamur.ai/free/en/papers/habash-2005-arabic-tokenization-part-speech-tagging/). In Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL’05), pages 573–580, Ann Arbor, Michigan.
11. Nizar Habash and Owen Rambow. 2006. [MAGEAD: A Morphological Analyzer and Generator for the Arabic Dialects](https://md.research.elamur.ai/free/en/papers/habash-2006-magead-morphological-analyzer-generator-arabic/). In Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics, pages 681–688, Sydney, Australia. [↗](https://doi.org/10.7916/d87s7x73)
12. Nizar Habash, Abdelhadi Soudi, and Tim Buckwalter. 2007. On Arabic Transliteration. In A. van den Bosch and A. Soudi, editors, Arabic Computational Morphology: Knowledge-based and Empirical Methods. Springer. [↗](https://doi.org/10.1007/978-1-4020-6046-5_2)
13. Nizar Habash, Ramy Eskander, and Abdelati Hawwari. 2012. [A Morphological Analyzer for Egyptian Arabic](https://md.research.elamur.ai/free/en/papers/habash-2012-morphological-analyzer-egyptian-arabic/). In Proceedings of the Twelfth Meeting of the Special Interest Group on Computational Morphology and Phonology, pages 1–9, Montréal, Canada.
14. Nizar Habash, Ryan Roth, Owen Rambow, Ramy Eskander, and Nadi Tomeh. 2013. [Morphological Analysis and Disambiguation for Dialectal Arabic](https://md.research.elamur.ai/free/en/papers/habash-2013-morphological-analysis-disambiguation-dialectal-arabic/). In Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT), Atlanta, GA.
15. Nizar Habash. 2007. Arabic Morphological Representations for Machine Translation. In A. van den Bosch and A. Soudi, editors, Arabic Computational Morphology: Knowledge-based and Empirical Methods. Springer. [↗](https://doi.org/10.1007/978-1-4020-6046-5_14)
16. Nizar Habash. 2010. Introduction to Arabic Natural Language Processing. Morgan & Claypool Publishers. [↗](https://doi.org/10.1007/978-3-031-02139-8)
17. Jan Hajič, Jan Hric, and Vladislav Kubon. 2000. Machine Translation of Very Close Languages. In Proceedings of the 6th Applied Natural Language Processing Conference (ANLP’2000), pages 7–12, Seattle. [find](https://scholar.google.com/scholar?q=Jan+Hajic%CC%8C%2C+Jan+Hric%2C+and+Vladislav+Kubon%2E+2000%2E+Machine+Translation+of+Very+Close+Languages%2E+In+Proceedings+of+the+6th+Applied+Natural+Language+Processing+Conference+%28ANLP%E2%80%992000%29%2C+pages+7%E2%80%9312%2C+Seattle%2E)
18. Philipp Koehn, Hieu Hoang, Alexandra Birch, Christopher Callison-Burch, Marcello Federico, Nicola Bertoldi, Brooke Cowan, Wade Shen, Christine Moran, Richard Zens, Christopher Dyer, Ondrej Bojar, Alexandra Constantin, and Evan Herbst. 2007. Moses: open source toolkit for statistical machine translation. In Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics Companion Volume Proceedings of the Demo and Poster Sessions, pages 177–180, Prague, Czech Republic. [find](https://scholar.google.com/scholar?q=Philipp+Koehn%2C+Hieu+Hoang%2C+Alexandra+Birch%2C+Christopher+Callison%2DBurch%2C+Marcello+Federico%2C+Nicola+Bertoldi%2C+Brooke+Cowan%2C+Wade+Shen%2C+Christine+Moran%2C+Richard+Zens%2C+Christopher+Dyer%2C+Ondrej+Bojar%2C+Alex)
19. Philipp Koehn. 2004. [Statistical significance tests for machine translation evaluation](https://md.research.elamur.ai/free/en/papers/koehn-2004-statistical-significance-tests-machine-translation/). In Proceedings of EMNLP 2004, pages 388–395, Barcelona, Spain, July. Association for Computational Linguistics.
20. Shankar Kumar, Franz J. Och, and Wolfgang Macherey. 2007. Improving word alignment with bridge languages. In Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL), pages 42–50, Prague, Czech Republic. [find](https://scholar.google.com/scholar?q=Shankar+Kumar%2C+Franz+J%2E+Och%2C+and+Wolfgang+Macherey%2E+2007%2E+Improving+word+alignment+with+bridge+languages%2E+In+Proceedings+of+the+2007+Joint+Conference+on+Empirical+Methods+in+Natural+Language+Processin)
21. Mohamed Maamouri, Ann Bies, Tim Buckwalter, and Wigdan Mekki. 2004. The Penn Arabic Treebank: Building a Large-Scale Annotated Arabic Corpus. In NEMLAR Conference on Arabic Language Resources and Tools, pages 102–109, Cairo, Egypt. [find](https://scholar.google.com/scholar?q=Mohamed+Maamouri%2C+Ann+Bies%2C+Tim+Buckwalter%2C+and+Wigdan+Mekki%2E+2004%2E+The+Penn+Arabic+Treebank%3A+Building+a+Large%2DScale+Annotated+Arabic+Corpus%2E+In+NEMLAR+Conference+on+Arabic+Language+Resources+and+Tool)
22. Preslav Nakov and Hwee Tou Ng. 2011. Translating from Morphologically Complex Languages: A Paraphrase-Based Approach. In Proceedings of the Meeting of the Association for Computational Linguistics (ACL’2011), Portland, Oregon, USA. [find](https://scholar.google.com/scholar?q=Preslav+Nakov+and+Hwee+Tou+Ng%2E+2011%2E+Translating+from+Morphologically+Complex+Languages%3A+A+Paraphrase%2DBased+Approach%2E+In+Proceedings+of+the+Meeting+of+the+Association+for+Computational+Linguistics+%28AC)
23. F. J. Och and H. Ney. 2003. A systematic comparison of various statistical alignment models. Computational Linguistics, 29(1):19–51. [↗](https://doi.org/10.1162/089120103321337421)
24. Franz Josef Och. 2003. Minimum Error Rate Training for Statistical Machine Translation. In Proceedings of the 41st Annual Conference of the Association for Computational Linguistics, pages 160–167, Sapporo, Japan. [find](https://scholar.google.com/scholar?q=Franz+Josef+Och%2E+2003%2E+Minimum+Error+Rate+Training+for+Statistical+Machine+Translation%2E+In+Proceedings+of+the+41st+Annual+Conference+of+the+Association+for+Computational+Linguistics%2C+pages+160%E2%80%93167%2C+Sa)
25. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. [BLEU: a Method for Automatic Evaluation of Machine Translation](https://md.research.elamur.ai/free/en/papers/papineni-2002-bleu-method-automatic-evaluation-machine/). In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pages 311–318, Philadelphia, PA.
26. Robert Parker, David Graff, Ke Chen, Junbo Kong, and Kazuaki Maeda. 2009. Arabic Gigaword Fourth Edition. LDC catalog number No. LDC2009T30, ISBN 1-58563-532-4. [↗](https://doi.org/10.35111/v9fm-zn61)
27. Jason Riesa and David Yarowsky. 2006. Minimally Supervised Morphological Segmentation with Applications to Machine Translation. In Proceedings of the 7th Conference of the Association for Machine Translation in the Americas (AMTA06), pages 185–192, Cambridge,MA. [find](https://scholar.google.com/scholar?q=Jason+Riesa+and+David+Yarowsky%2E+2006%2E+Minimally+Supervised+Morphological+Segmentation+with+Applications+to+Machine+Translation%2E+In+Proceedings+of+the+7th+Conference+of+the+Association+for+Machine+Tran)
28. Ryan Roth, Owen Rambow, Nizar Habash, Mona Diab, and Cynthia Rudin. 2008. [Arabic Morphological Tagging, Diacritization, and Lemmatization Using Lexeme Models and Feature Ranking](https://md.research.elamur.ai/free/en/papers/roth-2008-arabic-morphological-tagging-diacritization-lemmatization/). In Proceedings of ACL-08: HLT, Short Papers, pages 117–120, Columbus, Ohio.
29. Wael Salloum and Nizar Habash. 2011. [Dialectal to Standard Arabic Paraphrasing to Improve Arabic-English Statistical Machine Translation](https://md.research.elamur.ai/free/en/papers/salloum-2011-dialectal-standard-arabic-paraphrasing-improve/). In Proceedings of the First Workshop on Algorithms and Resources for Modelling of Dialects and Language Varieties, pages 10–21, Edinburgh, Scotland. [↗](https://doi.org/10.7916/d8697bg2)
30. Wael Salloum and Nizar Habash. 2012. [Elissa: A Dialectal to Standard Arabic Machine Translation System](https://md.research.elamur.ai/free/en/papers/salloum-2012-elissa-dialectal-standard-arabic-machine/). In Proceedings of the 24th International Conference on Computational Linguistics (COLING 2012): Demonstration Papers, pages 385–392, Mumbai, India.
31. Hassan Sawaf. 2010. [Arabic dialect handling in hybrid machine translation](https://md.research.elamur.ai/free/en/papers/sawaf-2010-arabic-dialect-handling-hybrid-machine/). In Proceedings of the Conference of the Association for Machine Translation in the Americas (AMTA), Denver, Colorado.
32. Andreas Stolcke. 2002. SRILM an Extensible Language Modeling Toolkit. In Proceedings of the International Conference on Spoken Language Processing. [find](https://scholar.google.com/scholar?q=Andreas+Stolcke%2E+2002%2E+SRILM+an+Extensible+Language+Modeling+Toolkit%2E+In+Proceedings+of+the+International+Conference+on+Spoken+Language+Processing%2E)
33. Masao Utiyama and Hitoshi Isahara. 2007. [A comparison of pivot methods for phrase-based statistical machine translation](https://md.research.elamur.ai/free/en/papers/utiyama-2007-comparison-pivot-methods-phrase-based/). In HLT-NAACL, pages 484–491.
34. Rabih Zbib, Erika Malchiodi, Jacob Devlin, David Stallard, Spyros Matsoukas, Richard Schwartz, John Makhoul, Omar F. Zaidan, and Chris Callison-Burch. 2012. [Machine Translation of Arabic Dialects](https://md.research.elamur.ai/free/en/papers/zbib-2012-machine-translation-arabic-dialects/). In Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 49– 59, Montréal, Canada, June. Association for Computational Linguistics.
35. Xiaoheng Zhang. 1998. Dialect MT: a case study between Cantonese and Mandarin. In Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics, ACL ’98, pages 1460– 1464, Montreal, Canada. [find](https://scholar.google.com/scholar?q=Xiaoheng+Zhang%2E+1998%2E+Dialect+MT%3A+a+case+study+between+Cantonese+and+Mandarin%2E+In+Proceedings+of+the+36th+Annual+Meeting+of+the+Association+for+Computational+Linguistics+and+17th+International+Confere)

*Updated 1 November 2026*