---
title: "Improving English-Arabic Transliteration with Phonemic Memories"
description: "The authors argue that existing corpora built from linked Wikipedia entries mostly cover celebrities, mix… 50 references, cited by 2 papers here."
authors: ["Yuanhe Tian", "Renze Lou", "Xiangyu Pang", "Lianxi Wang", "Shengyi Jiang", "Yan Song"]
year: 2022
venue: "Findings of the Association for Computational Linguistics: EMNLP 2022"
source: "https://aclanthology.org/2022.findings-emnlp.238/"
doi: "10.18653/v1/2022.findings-emnlp.238"
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/tian-2022-improving-english-arabic-transliteration-phonemic/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/tian-2022-improving-english-arabic-transliteration-phonemic/)

[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/8/) / Improving English-Arabic Transliteration with Phonemic Memories

# Improving English-Arabic Transliteration with Phonemic Memories

**Authors:** [Yuanhe Tian](https://md.research.elamur.ai/free/en/authors/yuanhe-tian/), [Renze Lou](https://md.research.elamur.ai/free/en/authors/renze-lou/), Xiangyu Pang, Lianxi Wang, Shengyi Jiang and [Yan Song](https://md.research.elamur.ai/free/en/authors/yan-song/) · **Year:** 2022 · **Venue:** [Findings of the Association for Computational Linguistics: EMNLP 2022](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2022](https://md.research.elamur.ai/free/en/venues/findings/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.findings-emnlp.238/) · [PDF](https://aclanthology.org/2022.findings-emnlp.238.pdf) · [DOI 10.18653/v1/2022.findings-emnlp.238](https://doi.org/10.18653/v1/2022.findings-emnlp.238) · [OpenAlex](https://openalex.org/W4385573409)

**Citations:** 2 citations (OpenAlex, 2026-10-14) · 2 in our library, of the 149,439 papers whose bibliographies we read

## Summary
The paper addresses English-to-Arabic transliteration of ordinary people's names, which matters in places like the UAE, where many residents are foreign but official records use Arabic. The authors argue that existing corpora built from linked Wikipedia entries mostly cover celebrities, mix in other entity types, and are often not public. They therefore built EANames. Training names were crawled from LinkedIn profiles of people working in the UAE, then labelled by majority vote of commercial MT/transliteration systems, with human checks for the remaining names. A cleaner test set was mined from an English-Arabic news parallel corpus. On the modelling side, they add a phonemic memory module to standard LSTM and Transformer encoder-decoders. Each English letter is linked to candidate phonemic symbols from an inventory built from English and Arabic sound systems, and attention weighs those symbols before feeding them into the model. The memory-enhanced models beat their plain counterparts on every reported metric, which shows that explicit cross-language sound knowledge still helps neural seq2seq transliteration.

## Key points
- EANames training data: 117,434 unique crawled single-word names. Of these, 68,553 were auto-labelled when at least two of Google Translate, Bing Translate and Bing Transliteration agreed, and 36,668 were human-approved Bing transliterations. The final set has 105,221 pairs.
- Human annotation used two bilingual annotators who shared 10% of the data. Their Cohen's kappa was 0.934, and they resolved disagreements by discussion.
- The test set has 3,000 name pairs drawn from ISI's automatically extracted Arabic-English parallel corpus of news text (LDC2007T08; Xinhua and AFP news). Names were found with the Stanford CoreNLP English and Arabic NER taggers and then verified with transliteration systems and humans.
- Evaluation used MRR, ACC, F-score and MAP over the top-5 candidates. A Lookup Table baseline scored 0.00% on dev and 46.10% on test, which means the dev set has no overlap with training while nearly half of the test names were seen in training.
- In the ablation, replacing attention over phonemic symbols with a plain average hurt both backbones. Results were averaged over 5 seeds. One example drop: MRR fell from 93.34 to 92.10, against a no-memory baseline of 91.95.

## Interesting ideas
- Create silver labels by majority vote across several independent systems, and send only the items with no consensus to humans, who need just a yes/no judgment on one candidate.
- Stop crawling once the share of genuinely new items per batch flattens out, as a practical signal that the common vocabulary is saturated.
- Run a trivial lookup-table "model" to measure how much of each split is memorizable, so seen and unseen performance can be separated.
- Give the model a small explicit inventory of candidate symbols per input unit and learn context-dependent weights over them; the paper found this better than treating all candidates equally.
- Draw training and test data from deliberately different sources, using large noisy data for training and a smaller, verified set from another domain for testing.

## For Mova

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

- **I1** (learn): This matches the witness-parser silver pipeline, and adding a cheap human accept/reject step on the no-agreement leftovers could raise silver quality at low cost.
- **I2** (world): Tracking the novelty rate while harvesting entities or lexicon from Wikidata/WordNet sources would show when further collection stops paying off.
- **I3** (learn): A memorization baseline serves as a negative control for every evaluation split and shows whether gains come from generalization or from train/test overlap.
- **I4** (tokens): Candidate lemmas or morphological analyses per token could be scored by context-weighted attention, while the candidate list stays inspectable and explainable.
- **I5** (learn): Keeping evaluation treebanks or QA sets independent from silver training sources lowers the risk of scores inflated by sharing the same domain.

*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 Washington](https://md.research.elamur.ai/free/en/universities/university-of-washington/) — University, Seattle, United States · 402 works · 212,762 citations
- [University of Science and Technology of China](https://md.research.elamur.ai/free/en/universities/university-of-science-and-technology-of-china/) — University, Hefei, China · 145 works · 114,409 citations
- [Temple University](https://md.research.elamur.ai/free/en/universities/temple-university/) — University, Philadelphia, United States · 11 works · 24,319 citations
- [Guangdong University of Foreign Studies](https://md.research.elamur.ai/free/en/universities/guangdong-university-of-foreign-studies/) — University, Guangzhou, China · 2 works · 7 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works

🧭 Topics (2): [English](https://md.research.elamur.ai/free/en/topics/english/) · 2,379 works · [Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/) · 3,066 works

## Cite

Cite as: Yuanhe Tian, Renze Lou, Xiangyu Pang, Lianxi Wang, Shengyi Jiang and Yan Song. 2022. Improving English-Arabic Transliteration with Phonemic Memories. Findings of the Association for Computational Linguistics: EMNLP 2022.

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

```bibtex
@inproceedings{tian2022improving,
  title = {{Improving English-Arabic Transliteration with Phonemic Memories}},
  author = {Yuanhe Tian, Renze Lou, Xiangyu Pang, Lianxi Wang, Shengyi Jiang and Yan Song},
  booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2022},
  year = {2022},
  doi = {10.18653/v1/2022.findings-emnlp.238},
  url = {https://doi.org/10.18653/v1/2022.findings-emnlp.238}
}
```

- [← previous GOF at Qur'an QA 2022: Towards an Efficient Question Answering For The Holy Qu'ran In The Arabic Language Using Deep Learning-Based Approach](https://md.research.elamur.ai/free/en/papers/mostafa-2022-gof-qur-qa-2022-efficient/)
- [next → Joint Coreference Resolution for Zeros and non-Zeros in Arabic](https://md.research.elamur.ai/free/en/papers/aloraini-2022-joint-coreference-resolution-zeros-non/)
- [↑ back to papers of 2022](https://md.research.elamur.ai/free/en/papers/2022/page/8/)

## References

50 references, 12 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Mohamed Al-Badrashiny, Ramy Eskander, Nizar Habash, and Owen Rambow. 2014. [Automatic Transliteration of Romanized Dialectal Arabic](https://md.research.elamur.ai/free/en/papers/badrashiny-2014-automatic-transliteration-romanized-dialectal-arabic/). In Proceedings of the Eighteenth Conference on Computational Natural Language Learning, pages 30–38, Ann Arbor, Michigan.
2. Yaser Al-Onaizan and Kevin Knight. 2002. [Machine Transliteration of Names in Arabic Texts](https://md.research.elamur.ai/free/en/papers/onaizan-2002-machine-transliteration-names-arabic-texts/). In Proceedings of the ACL-02 Workshop on Computational Approaches to Semitic Languages, Philadelphia, Pennsylvania, USA.
3. Manar Alkhatib and Khaled Shaalan. 2020. Boosting Arabic Named Entity Recognition Transliteration with Deep Learning. In The thirty-third international flairs conference. [find](https://scholar.google.com/scholar?q=Manar+Alkhatib+and+Khaled+Shaalan%2E+2020%2E+Boosting+Arabic+Named+Entity+Recognition+Transliteration+with+Deep+Learning%2E+In+The+thirty%2Dthird+international+flairs+conference%2E)
4. Faisal Alshuwaier and Ali Areshey. 2011. [Translating English Names to Arabic Using Phonotactic Rules](https://md.research.elamur.ai/free/en/papers/alshuwaier-2011-translating-english-names-arabic-phonotactic/). In Proceedings of the 25th Pacific Asia Conference on Language, Information and Computation, pages 485–492, Singapore.
5. M. Arbabi, S. M. Fischthal, V. C. Cheng, and E. Bart. 1994. Algorithms for Arabic Name Transliteration. IBM Journal of Research and Development, 38(2):183–194. [↗](https://doi.org/10.1147/rd.382.0183)
6. Fernando Benites, Gilbert François Duivesteijn, Pius von Däniken, and Mark Cieliebak. 2020. Translit: A Large-scale Name Transliteration Resource. In Proceedings of the 12th Language Resources and Evaluation Conference, pages 3265–3271. [find](https://scholar.google.com/scholar?q=Fernando+Benites%2C+Gilbert+Fran%C3%A7ois+Duivesteijn%2C+Pius+von+D%C3%A4niken%2C+and+Mark+Cieliebak%2E+2020%2E+Translit%3A+A+Large%2Dscale+Name+Transliteration+Resource%2E+In+Proceedings+of+the+12th+Language+Resources+and+Eva)
7. Achraf Chalabi and Hany Gerges. 2012. [Romanized Arabic Transliteration](https://md.research.elamur.ai/free/en/papers/chalabi-2012-romanized-arabic-transliteration/). In Proceedings of the Second Workshop on Advances in Text Input Methods, pages 89–96, Mumbai, India.
8. Guimin Chen, Yuanhe Tian, Yan Song, and Xiang Wan. 2021. Relation Extraction with Type-aware Map Memories of Word Dependencies. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 2501–2512, Online. [find](https://scholar.google.com/scholar?q=Guimin+Chen%2C+Yuanhe+Tian%2C+Yan+Song%2C+and+Xiang+Wan%2E+2021%2E+Relation+Extraction+with+Type%2Daware+Map+Memories+of+Word+Dependencies%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+ACL%2DIJCNLP)
9. Nancy Chen, Rafael E. Banchs, Min Zhang, Xiangyu Duan, and Haizhou Li. 2018. Report of NEWS 2018 Named Entity Transliteration Shared Task. In Proceedings of the Seventh Named Entities Workshop, pages 55–73, Melbourne, Australia. [find](https://scholar.google.com/scholar?q=Nancy+Chen%2C+Rafael+E%2E+Banchs%2C+Min+Zhang%2C+Xiangyu+Duan%2C+and+Haizhou+Li%2E+2018%2E+Report+of+NEWS+2018+Named+Entity+Transliteration+Shared+Task%2E+In+Proceedings+of+the+Seventh+Named+Entities+Workshop%2C+pages+)
10. Yanqing Chen and Steven Skiena. 2016. False-friend Detection and Entity Matching via Unsupervised Transliteration. arXiv preprint arXiv:1611.06722. [↗](https://arxiv.org/abs/1611.06722)
11. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://md.research.elamur.ai/free/en/papers/devlin-2019-bert-pre-training-deep-bidirectional/). In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 4171–4186. [↗](https://doi.org/10.18653/v1/n19-1423)
12. Shizhe Diao, Jiaxin Bai, Yan Song, Tong Zhang, and Yonggang Wang. 2020. ZEN: Pre-training Chinese Text Encoder Enhanced by N-gram Representations. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 4729–4740. [find](https://scholar.google.com/scholar?q=Shizhe+Diao%2C+Jiaxin+Bai%2C+Yan+Song%2C+Tong+Zhang%2C+and+Yonggang+Wang%2E+2020%2E+ZEN%3A+Pre%2Dtraining+Chinese+Text+Encoder+Enhanced+by+N%2Dgram+Representations%2E+In+Findings+of+the+Association+for+Computational+Ling)
13. Shizhe Diao, Ruijia Xu, Hongjin Su, Yilei Jiang, Yan Song, and Tong Zhang. 2021. Taming Pre-trained Language Models with N-gram Representations for Low-Resource Domain Adaptation. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 3336–3349, Online. [find](https://scholar.google.com/scholar?q=Shizhe+Diao%2C+Ruijia+Xu%2C+Hongjin+Su%2C+Yilei+Jiang%2C+Yan+Song%2C+and+Tong+Zhang%2E+2021%2E+Taming+Pre%2Dtrained+Language+Models+with+N%2Dgram+Representations+for+Low%2DResource+Domain+Adaptation%2E+In+Proceedings+of+th)
14. Andrew Finch, Lemao Liu, Xiaolin Wang, and Eiichiro Sumita. 2016. Target-Bidirectional Neural Models for Machine Transliteration. In Proceedings of the Sixth Named Entity Workshop, pages 78–82, Berlin, Germany. [find](https://scholar.google.com/scholar?q=Andrew+Finch%2C+Lemao+Liu%2C+Xiaolin+Wang%2C+and+Eiichiro+Sumita%2E+2016%2E+Target%2DBidirectional+Neural+Models+for+Machine+Transliteration%2E+In+Proceedings+of+the+Sixth+Named+Entity+Workshop%2C+pages+78%E2%80%9382%2C+Berlin)
15. Roman Grundkiewicz and Kenneth Heafield. 2018. Neural Machine Translation Techniques for Named Entity Transliteration. In Proceedings of the Seventh Named Entities Workshop, pages 89–94, Melbourne, Australia. [find](https://scholar.google.com/scholar?q=Roman+Grundkiewicz+and+Kenneth+Heafield%2E+2018%2E+Neural+Machine+Translation+Techniques+for+Named+Entity+Transliteration%2E+In+Proceedings+of+the+Seventh+Named+Entities+Workshop%2C+pages+89%E2%80%9394%2C+Melbourne%2C+Au)
16. Imane Guellil, Faiçal Azouaou, Mourad Abbas, and Sadat Fatiha. 2017. Arabizi Transliteration of Algerian Arabic Dialect into Modern Standard Arabic. Social MT, pages 1–8. [find](https://scholar.google.com/scholar?q=Imane+Guellil%2C+Fai%C3%A7al+Azouaou%2C+Mourad+Abbas%2C+and+Sadat+Fatiha%2E+2017%2E+Arabizi+Transliteration+of+Algerian+Arabic+Dialect+into+Modern+Standard+Arabic%2E+Social+MT%2C+pages+1%E2%80%938%2E)
17. Nizar Habash, Abdelhadi Soudi, and Timothy Buckwalter. 2007. On Arabic Transliteration, pages 15–22. Dordrecht. [find](https://scholar.google.com/scholar?q=Nizar+Habash%2C+Abdelhadi+Soudi%2C+and+Timothy+Buckwalter%2E+2007%2E+On+Arabic+Transliteration%2C+pages+15%E2%80%9322%2E+Dordrecht%2E)
18. Mohamed Seghir Hadj Ameur, Farid Meziane, and Ahmed Guessoum. 2017. Arabic Machine Transliteration using an Attention-based Encoder-decoder Model. Procedia Computer Science, 117:287–297. Arabic Computational Linguistics. [find](https://scholar.google.com/scholar?q=Mohamed+Seghir+Hadj+Ameur%2C+Farid+Meziane%2C+and+Ahmed+Guessoum%2E+2017%2E+Arabic+Machine+Transliteration+using+an+Attention%2Dbased+Encoder%2Ddecoder+Model%2E+Procedia+Computer+Science%2C+117%3A287%E2%80%93297%2E+Arabic+Comput)
19. Jialong Han, Yan Song, Wayne Xin Zhao, Shuming Shi, and Haisong Zhang. 2018. Hyperdoc2vec: Distributed Representations of Hypertext Documents. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2384–2394, Melbourne, Australia. [find](https://scholar.google.com/scholar?q=Jialong+Han%2C+Yan+Song%2C+Wayne+Xin+Zhao%2C+Shuming+Shi%2C+and+Haisong+Zhang%2E+2018%2E+Hyperdoc2vec%3A+Distributed+Representations+of+Hypertext+Documents%2E+In+Proceedings+of+the+56th+Annual+Meeting+of+the+Associat)
20. Parag Jain and Mirella Lapata. 2021. Memory-Based Semantic Parsing. Transactions of the Association for Computational Linguistics, 9:1197–1212. [↗](https://doi.org/10.1162/tacl_a_00422)
21. Kevin Knight and Jonathan Graehl. 1998. [Machine Transliteration](https://md.research.elamur.ai/free/en/papers/knight-1998-machine-transliteration/). Computational Linguistics, 24(4):599–612.
22. Pankaj Kumar and V Kumar. 2013. Statistical Machine Translation based Punjabi to English Transliteration System for Proper Nouns. International Journal of Application or Innovation in Engineering & Management, 2(8):318–321. [find](https://scholar.google.com/scholar?q=Pankaj+Kumar+and+V+Kumar%2E+2013%2E+Statistical+Machine+Translation+based+Punjabi+to+English+Transliteration+System+for+Proper+Nouns%2E+International+Journal+of+Application+or+Innovation+in+Engineering+%26+Ma)
23. A Kumaran, Mitesh M. Khapra, and Haizhou Li. 2010. Report of NEWS 2010 Transliteration Mining Shared Task. In Proceedings of the 2010 Named Entities Workshop, pages 21–28, Uppsala, Sweden. [find](https://scholar.google.com/scholar?q=A+Kumaran%2C+Mitesh+M%2E+Khapra%2C+and+Haizhou+Li%2E+2010%2E+Report+of+NEWS+2010+Transliteration+Mining+Shared+Task%2E+In+Proceedings+of+the+2010+Named+Entities+Workshop%2C+pages+21%E2%80%9328%2C+Uppsala%2C+Sweden%2E)
24. Soumyadeep Kundu, Sayantan Paul, and Santanu Pal. 2018. A Deep Learning Based Approach to Transliteration. In Proceedings of the Seventh Named Entities Workshop, pages 79–83, Melbourne, Australia. [find](https://scholar.google.com/scholar?q=Soumyadeep+Kundu%2C+Sayantan+Paul%2C+and+Santanu+Pal%2E+2018%2E+A+Deep+Learning+Based+Approach+to+Transliteration%2E+In+Proceedings+of+the+Seventh+Named+Entities+Workshop%2C+pages+79%E2%80%9383%2C+Melbourne%2C+Australia%2E)
25. Ngoc Tan Le, Fatiha Sadat, Lucie Menard, and Dien Dinh. 2019. Low-Resource Machine Transliteration Using Recurrent Neural Networks. 18(2). Conference on Empirical Methods in Natural Language Processing, pages 1400–1409. [↗](https://doi.org/10.1145/3265752)
26. Molly Moran and Constantine Lignos. 2020. Effective Architectures for Low Resource Multilingual Named Entity Transliteration. In Proceedings of the 3rd Workshop on Technologies for MT of Low Resource Languages, pages 79–86, Suzhou, China. [find](https://scholar.google.com/scholar?q=Molly+Moran+and+Constantine+Lignos%2E+2020%2E+Effective+Architectures+for+Low+Resource+Multilingual+Named+Entity+Transliteration%2E+In+Proceedings+of+the+3rd+Workshop+on+Technologies+for+MT+of+Low+Resource+)
27. Nikitha Murikinati, Antonios Anastasopoulos, and Graham Neubig. 2020. Transliteration for Cross-lingual Morphological Inflection. In Proceedings of the 17th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology. [find](https://scholar.google.com/scholar?q=Nikitha+Murikinati%2C+Antonios+Anastasopoulos%2C+and+Graham+Neubig%2E+2020%2E+Transliteration+for+Cross%2Dlingual+Morphological+Inflection%2E+In+Proceedings+of+the+17th+SIGMORPHON+Workshop+on+Computational+Resear)
28. Yuyang Nie, Yuanhe Tian, Yan Song, Xiang Ao, and Xiang Wan. 2020. Improving Named Entity Recognition with Attentive Ensemble of Syntactic Information. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 4231–4245. [find](https://scholar.google.com/scholar?q=Yuyang+Nie%2C+Yuanhe+Tian%2C+Yan+Song%2C+Xiang+Ao%2C+and+Xiang+Wan%2E+2020%2E+Improving+Named+Entity+Recognition+with+Attentive+Ensemble+of+Syntactic+Information%2E+In+Findings+of+the+Association+for+Computational+)
29. Jong-Hoon Oh, Key-Sun Choi, and Hitoshi Isahara. 2006. A Machine Transliteration Model Based on Correspondence between Graphemes and Phonemes. ACM Transactions on Asian Language Information Processing, 5(3):185–208. [↗](https://doi.org/10.1145/1194936.1194938)
30. Vladimir Pervouchine, Haizhou Li, and Bo Lin. 2009. Transliteration Alignment. In Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP, pages 136–144, Suntec, Singapore. [find](https://scholar.google.com/scholar?q=Vladimir+Pervouchine%2C+Haizhou+Li%2C+and+Bo+Lin%2E+2009%2E+Transliteration+Alignment%2E+In+Proceedings+of+the+Joint+Conference+of+the+47th+Annual+Meeting+of+the+ACL+and+the+4th+International+Joint+Conference+o)
31. Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Veselin Stoyanov, and Luke Zettlemoyer. 2020. [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://md.research.elamur.ai/free/en/papers/lewis-2020-bart-denoising-sequence-sequence-pre/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7871–7880, Online.
32. Han Qin, Guimin Chen, Yuanhe Tian, and Yan Song. 2021. [Improving Arabic Diacritization with Regularized Decoding and Adversarial Training](https://md.research.elamur.ai/free/en/papers/qin-2021-improving-arabic-diacritization-regularized-decoding/). In Proceedings of the Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing.
33. Haizhou Li, Min Zhang, and Jian Su. 2004. [A Joint Source-Channel Model for Machine Transliteration](https://md.research.elamur.ai/free/en/papers/li-2004-joint-source-channel-model-machine/). In Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics (ACL-04), pages 159–166, Barcelona, Spain.
34. Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever, et al. 2019. Language Models are Unsupervised Multitask Learners. OpenAI blog, 1(8):9. [find](https://scholar.google.com/scholar?q=Alec+Radford%2C+Jeffrey+Wu%2C+Rewon+Child%2C+David+Luan%2C+Dario+Amodei%2C+Ilya+Sutskever%2C+et+al%2E+2019%2E+Language+Models+are+Unsupervised+Multitask+Learners%2E+OpenAI+blog%2C+1%288%29%3A9%2E)
35. Christopher D Manning, Mihai Surdeanu, John Bauer, Jenny Rose Finkel, Steven Bethard, and David Mc-Closky. 2014. [The Stanford CoreNLP Natural Language Processing Toolkit](https://md.research.elamur.ai/free/en/papers/manning-2014-stanford-corenlp-natural-language-processing/). In Proceedings of 52nd annual meeting of the association for computational linguistics: system demonstrations, pages 55–60.
36. Yuval Merhav and Stephen Ash. 2018. Design Challenges in Named Entity Transliteration. In Proceedings of the 27th international conference on computational linguistics, pages 630–640. [↗](https://doi.org/10.48550/arxiv.1808.02563)
37. Alexander Miller, Adam Fisch, Jesse Dodge, Amir-Hossein Karimi, Antoine Bordes, and Jason Weston. 2016. Key-Value Memory Networks for Directly Reading Documents. In Proceedings of the 2016 [find](https://scholar.google.com/scholar?q=Alexander+Miller%2C+Adam+Fisch%2C+Jesse+Dodge%2C+Amir%2DHossein+Karimi%2C+Antoine+Bordes%2C+and+Jason+Weston%2E+2016%2E+Key%2DValue+Memory+Networks+for+Directly+Reading+Documents%2E+In+Proceedings+of+the+2016)
38. Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, Peter J Liu, et al. 2020. [Exploring the Limits of Transfer Learning with a Unified Text-to-text Transformer](https://md.research.elamur.ai/free/en/papers/raffel-2019-exploring-limits-transfer-learning-unified/). J. Mach. Learn. Res., 21(140):1–67. [↗](https://doi.org/10.48550/arxiv.1910.10683)
39. Sujith Ravi and Kevin Knight. 2009. Learning Phoneme Mappings for Transliteration without Parallel Data. In Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, pages 37–45, Boulder, Colorado. [find](https://scholar.google.com/scholar?q=Sujith+Ravi+and+Kevin+Knight%2E+2009%2E+Learning+Phoneme+Mappings+for+Transliteration+without+Parallel+Data%2E+In+Proceedings+of+Human+Language+Technologies%3A+The+2009+Annual+Conference+of+the+North+American)
40. Mihaela Rosca and Thomas Breuel. 2016. Sequence-to-sequence Neural Network Models for Transliteration. arXiv preprint arXiv:1610.09565. [↗](https://arxiv.org/abs/1610.09565)
41. Yan Song and Chunyu Kit. 2010. Does Joint Decoding Really Outperform Cascade Processing in English-to-Chinese Transliteration Generation? The Role of Syllabification. In 2010 International Conference on Machine Learning and Cybernetics, volume 6, pages 3323–3328. [find](https://scholar.google.com/scholar?q=Yan+Song+and+Chunyu+Kit%2E+2010%2E+Does+Joint+Decoding+Really+Outperform+Cascade+Processing+in+English%2Dto%2DChinese+Transliteration+Generation%3F+The+Role+of+Syllabification%2E+In+2010+International+Conference+)
42. Yan Song, Chunyu Kit, and Xiao Chen. 2009. Transliteration of Name Entity via Improved Statistical Translation on Character Sequences. In Proceedings of the 2009 Named Entities Workshop: Shared Task on Transliteration (NEWS 2009), pages 57–60, Suntec, Singapore. [find](https://scholar.google.com/scholar?q=Yan+Song%2C+Chunyu+Kit%2C+and+Xiao+Chen%2E+2009%2E+Transliteration+of+Name+Entity+via+Improved+Statistical+Translation+on+Character+Sequences%2E+In+Proceedings+of+the+2009+Named+Entities+Workshop%3A+Shared+Task+o)
43. Yan Song, Tong Zhang, Yonggang Wang, and Kai-Fu Lee. 2021. ZEN 2.0: Continue Training and Adaption for N-gram Enhanced Text Encoders. arXiv preprint arXiv:2105.01279. [↗](https://arxiv.org/abs/2105.01279)
44. Niket Tandon, Aman Madaan, Peter Clark, and Yiming Yang. 2022. Learning to Repair: Repairing Model Output Errors after Deployment Using a Dynamic Memory of Feedback. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 339–352, Seattle, United States. [find](https://scholar.google.com/scholar?q=Niket+Tandon%2C+Aman+Madaan%2C+Peter+Clark%2C+and+Yiming+Yang%2E+2022%2E+Learning+to+Repair%3A+Repairing+Model+Output+Errors+after+Deployment+Using+a+Dynamic+Memory+of+Feedback%2E+In+Findings+of+the+Association+for)
45. Yuanhe Tian, Guimin Chen, and Yan Song. 2021. Enhancing Aspect-level Sentiment Analysis with Word Dependencies. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 3726–3739, Online. [find](https://scholar.google.com/scholar?q=Yuanhe+Tian%2C+Guimin+Chen%2C+and+Yan+Song%2E+2021%2E+Enhancing+Aspect%2Dlevel+Sentiment+Analysis+with+Word+Dependencies%2E+In+Proceedings+of+the+16th+Conference+of+the+European+Chapter+of+the+Association+for+Com)
46. Yuanhe Tian, Han Qin, Fei Xia, and Yan Song. 2022. Syntax-driven Approach for Semantic Role Labeling. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 7129–7139. [find](https://scholar.google.com/scholar?q=Yuanhe+Tian%2C+Han+Qin%2C+Fei+Xia%2C+and+Yan+Song%2E+2022%2E+Syntax%2Ddriven+Approach+for+Semantic+Role+Labeling%2E+In+Proceedings+of+the+Thirteenth+Language+Resources+and+Evaluation+Conference%2C+pages+7129%E2%80%937139%2E)
47. Yuanhe Tian, Wang Shen, Yan Song, Fei Xia, Min He, and Kenli Li. 2020a. Improving Biomedical Named Entity Recognition with Syntactic Information. BMC Bioinformatics, 21:1471–2105. [↗](https://doi.org/10.1186/s12859-020-03834-6)
48. Yuanhe Tian, Yan Song, and Fei Xia. 2020b. Joint Chinese Word Segmentation and Part-of-speech Tagging via Multi-channel Attention of Character N-grams. In Proceedings of the 28th International Conference on Computational Linguistics, pages 2073–2084. [find](https://scholar.google.com/scholar?q=Yuanhe+Tian%2C+Yan+Song%2C+and+Fei+Xia%2E+2020b%2E+Joint+Chinese+Word+Segmentation+and+Part%2Dof%2Dspeech+Tagging+via+Multi%2Dchannel+Attention+of+Character+N%2Dgrams%2E+In+Proceedings+of+the+28th+International+Confere)
49. Shyam Upadhyay, Jordan Kodner, and Dan Roth. 2018. Bootstrapping Transliteration with Constrained Discovery for Low-resource Languages. arXiv preprint arXiv:1809.07807. [↗](https://arxiv.org/abs/1809.07807)
50. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. [Attention is All You Need](https://md.research.elamur.ai/free/en/papers/vaswani-2017-attention-all-need/). Advances in neural information processing systems, 30.

*Updated 1 November 2026*