My Connection to Persian and Iranian Languages

Persian and its sister languages hold a very special place in my heart. Growing up in a household adorned with countless old books, especially poetry collections, I was captivated by the literary world from an early age. As a child, I would often find solace in solitude, sitting quietly and immersing myself in the verses of Rumi, Khayyam, Rudaki, and Khaqani. It was an enchanting experience that I still yearn to relive.

To this day, poetry remains an important part of my life, and one of the websites I especially enjoy visiting is Ganjoor, a remarkable archive of Persian poetry. This deep personal connection evolved into a lasting passion for language, culture, and meaning, which eventually led me toward multilingual NLP. I feel especially fortunate to have had the opportunity to work on multilingual NLP during my PhD, including research involving Persian and related languages, such as temporal tagging for Persian (Mirzababaei et al., 2022) and language models covering many Iranian languages (ImaniGooghari et al., 2023).

Beyond my professional work, in my free time I also lead an open-source community focused on Iranian languages through SIGIranic, where we work to support resources, tools, and collaboration for these languages.

References

AACL 2022
Hengam: An Adversarially Trained Transformer for Persian Temporal Tagging

Sajad Mirzababaei, Amir Hossein Kargaran, Hinrich Schütze, and 1 more author

In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), 2022

Abs Bib ACL PDF Video Code

Hengam is an adversarially trained transformer for Persian temporal tagging. We build a rule-based tagger to weakly label a large, diverse Persian corpus, train a transformer that generalizes beyond the rules, and release HengamGold, the first high-quality gold standard for the task. Hengam reaches a type F1 of 95.42 and handles ambiguity and misspellings.
@inproceedings{kargaran-2022-hengam, title = {{H}engam: An Adversarially Trained Transformer for {P}ersian Temporal Tagging}, author = {Mirzababaei, Sajad and Kargaran, Amir Hossein and Sch{\"u}tze, Hinrich and Asgari, Ehsaneddin}, booktitle = {Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)}, year = {2022}, pages = {1013--1024}, publisher = {Association for Computational Linguistics}, address = {Online only}, }
ACL 2023
Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages

Ayyoob ImaniGooghari, Peiqin Lin, Amir Hossein Kargaran, and 8 more authors

In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2023

Abs Area Chair Award Oral Presentation arXiv Bib ACL PDF Code

Instead of making LLMs better for 100 languages, we scale them horizontally. We build Glot500-c, a corpus for 511 mostly low-resource languages, and continue pretraining to create Glot500-m, which improves substantially over XLM-R on five tasks. Representation quality depends on a mix of factors, including corpus size, script, related languages and model capacity.
@inproceedings{imanigooghari-2023-glot, title = {{Glot500}: Scaling Multilingual Corpora and Language Models to 500 Languages}, author = {ImaniGooghari, Ayyoob and Lin, Peiqin and Kargaran, Amir Hossein and Severini, Silvia and Sabet, Masoud Jalili and Kassner, Nora and Ma, Chunlan and Schmid, Helmut and Martins, Andr{\'e} and Yvon, Fran{\c{c}}ois and Sch{\"u}tze, Hinrich}, booktitle = {Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, year = {2023}, publisher = {Association for Computational Linguistics}, address = {Toronto, Canada}, }