Sina Ahmadi
Researcher
Sina Ahmadi
GitHub Email ORCID Google Scholar Stack Overflow Twitter FOAF Zurich, Switzerland RSS
Projects
Current projects
|
MUTAMUR |
| Feb. 2024- | |
| In the MUTAMUR project (Multitask Learning with Multilingual Resources for Better Natural Language Understanding), we investigate methods for knowledge sharing and transfer between machine learning models in natural language processing. | |
|
DOLMA-NLP |
| Sep. 2024-Feb. 2025 | |
| I am privileged to be among the selected practitioners of the prestigious Stanford Initiative on Language Inclusion and Conservation in Old and New Media (SILICON) to focus on developing technologies for Middle Eastern languages! |
Past projects
|
George Mason NLP |
| Sep. 2022-Jan. 2024 | |
| I was very lucky to work at GMNLP on various topics in language technology in low-resource setups with rewarding experiences in research, supervision and teaching. | |
|
Kurdish Langauge Processing Toolkit |
| 2020- | |
| KLPT-Kurdish Language Processing Toolkit is a natural language processing (NLP) toolkit in Python for the Kurdish language. It comes with core modules for language processing, such as preprocessing, stemming, transliteration and tokenizion, spell-checking and morphological analysis of various dialects of Kurdish. | |
|
ELEXIS - European Lexicographic Infrastructure |
| 2018-2022 | |
|
Linking lexical resources is a challenge that requires impractical amounts of human efforts, but is still not easy to solve automatically. We develop methods that will make the linking problem viable for large resources, by using state-of-the-art semantic and natural language processing techniques. Our approaches are integrated as a single automated linking tool called NAISC /naʃk/ which facilitates any linking problem for any type of input, from tabular to ontological. Thank to ELEXIS and all colleagues who accomplished such an amazing project!
|
|
|
NexusLinguarum |
| 2021-2022 | |
| I was a member of the WG1 focusing on cross-lingual data interlinking, access and retrieval in the Linguistic Linked Open Data (LLOD). | |
|
XƎLATEX for Kurdish |
| 2019-2020 | |
| This project started as a weekend project. Could you believe it was not possible to write a proper document in Kurdish in any of TeX engines without using the Persian or Arabic packages? Well, I spent quite a while adding Kurdish to Polyglossia and Babel. Find a bunch of sample documents here. | |
|
Kurdish Basic Language Resource Kit (BLARK) |
| 2017-2020 | |
| The Kurdish BLARK (Basic Language Resource Kit) aims at providing resources for the Kurdish language. As a project leader, I was involved in the development of resources and technology for Kurdish language processing, including electronic lexicons based on Ontolex-Lemon, corpus of oral material and parallel corpora. A few particular examples are the Kurdish Folkloric Lyrics Corpus and Kurdish parallel corpora. | |
|
Kurdish Language Processing Project (KLPP) |
| 2013 | |
| As a bachelor's student, I was a volunteer in this project mostly by providing linguistic support regarding the Sorani dialect of Kurdish for implementing fundamental tools for Kurdish processing and resources such as KurdNet–the Kurdish WordNet. For the latter, I translated the Princeton WordNet synsets and definitions into Sorani. I believe this was a remarkable project as a pioneer in Kurdish language processing from 2009. |
Sina Ahmadi
Researcher
Sina Ahmadi