Papers by Sina Ahmadi

12 papers
Dia-Lingle: A Gamified Interface for Dialectal Data Collection (2025.acl-demo)

Copied to clipboard

Challenge: Dialects suffer from the scarcity of textual resources and are largely spoken rather than written.
Approach: They propose a gamified interface that combines active learning with gamification to enhance the dialect corpus.
Outcome: The proposed interface demonstrates high levels of user satisfaction while requiring minimal effort.
Parity-Aware Byte-Pair Encoding: Improving Cross-lingual Fairness in Tokenization (2026.acl-long)

Copied to clipboard

Challenge: Tokenization is the first step of most NLP pipelines.
Approach: They propose a parity-aware byte pair encoder that maximizes the compression gain of the currently worst-compressed language for cross-lingual parity.
Outcome: a new algorithm reduces tokenization inequality by 89% compared to classical BPE . the proposed algorithm is based on a fair-max rule that maximizes the compression gain of the currently worst-compressed language .
SwiLTra-Bench: The Swiss Legal Translation Benchmark (2025.acl-long)

Copied to clipboard

Challenge: In Switzerland legal translation relies on legal experts who must be both legal experts and skilled translators—creating bottlenecks and impacting effective access to justice.
Approach: They propose a multilingual benchmarking system that evaluates Swiss legal translation systems based on 180K aligned Swiss legal translator pairs . they show frontier models achieve superior translation performance across all document types while specialized translation systems excel specifically in laws but under-perform in headnotes.
Outcome: The proposed model outperforms specialized models in laws but underperform in headnotes.
Cross-Lingual Link Discovery for Under-Resourced Languages (2022.lrec-1)

Copied to clipboard

Challenge: Linked data paradigms can be used to solve under-resourced languages' problem of under-utilization of resources.
Approach: They propose a paradigm for cross-lingual link discovery that can be applied to under-resourced languages . they argue that techniques for cross language linking can be readily applied .
Outcome: The proposed technologies can be applied to under-resourced languages, the authors argue . the authors show that the Linked Data paradigm can be used to solve the problem .
ConLoan: A Contrastive Multilingual Dataset for Evaluating Loanwords (2025.acl-long)

Copied to clipboard

Challenge: Lexical borrowing is a ubiquitous linguistic phenomenon influenced by geopolitical, societal, and technological factors.
Approach: They propose a novel contrastive dataset comprising sentences with and without loanwords across 10 languages to examine how machine translation and language models process loanword .
Outcome: The proposed dataset shows that state-of-the-art models prefer loanwords over native terms and exhibit varying performance across languages.
Language and Speech Technology for Central Kurdish Varieties (2024.lrec-main)

Copied to clipboard

Challenge: a recent study focused on the Kurdish language, a less-resourced Indo-European language spoken by over 30 million speakers.
Approach: They propose to develop resources for language and speech technology for Kurdish . they report the performance of machine translation, automatic speech recognition and language identification .
Outcome: The proposed model is based on transcribing movies and TV series as an alternative to fieldwork.
A Multilingual Evaluation Dataset for Monolingual Word Sense Alignment (2020.lrec-1)

Copied to clipboard

Challenge: a new dataset aims to align monolingual dictionaries with a single sense level for 15 languages . this dataset covers a wide range of languages and resources .
Approach: They propose to manually align monolingual dictionaries with possible semantic relationships . they use 15 languages to create a new baseline for the task of monolingual word sense alignment .
Outcome: The proposed dataset covers 15 languages and covers the more challenging task of linking general-purpose language.
CODET: A Benchmark for Contrastive Dialectal Evaluation of Machine Translation (2024.findings-eacl)

Copied to clipboard

Challenge: Neural machine translation systems exhibit limited robustness in handling source-side linguistic variations.
Approach: They propose a dialectal benchmark to quantify the robustness of MT systems to handle source-side linguistic variations.
Outcome: The proposed benchmark demonstrates that large MT models face challenges translating dialectal variants.
PARME: Parallel Corpora for Low-Resourced Middle Eastern Languages (2025.acl-long)

Copied to clipboard

Challenge: UNESCO has identified 60 varieties of Middle Eastern languages as underrepresented . a limited availability of language technology perpetuates a cycle of digital exclusion .
Approach: They develop a parallel corpora for eight severely under-resourced varieties in the region . they evaluate machine translation capabilities through zero-shot approaches and fine-tuning experiments .
Outcome: The proposed model aims to improve the processing of the eight under-resourced languages in the Middle East.
Script Normalization for Unconventional Writing of Under-Resourced Languages in Bilingual Communities (2023.acl-long)

Copied to clipboard

Challenge: linguistically under-represented communities have an extraordinary opportunity to create content in their native languages.
Approach: They propose to solve the problem of script normalization for languages written in a Perso-Arabic script and use a transformer-based model to analyze the noise levels.
Outcome: The proposed model can normalize a language written in a Perso-Arabic script and improve machine translation and language identification tasks.
CoFiF Plus: A French Financial Narrative Summarisation Corpus (2022.lrec-1)

Copied to clipboard

Challenge: Existing corpora for financial narrative summarisation exists in English but there is a significant lack of financial text resources in the French language.
Approach: They propose to use natural language processing to analyse financial documents to find the best summarisation methods.
Outcome: The proposed dataset is the first to provide a comprehensive set of financial text written in French.
Defying Wikidata: Validation of Terminological Relations in the Web of Data (2020.lrec-1)

Copied to clipboard

Challenge: a new approach to validate terminological data retrieved from open encyclopaedic knowledge bases is needed . the legal domain is one of the most valuable areas of knowledge in the world .
Approach: They propose to validate terminological data retrieved from open encyclopaedic knowledge bases by enriching them with information from existing resources in the Semantic Web.
Outcome: The proposed method validates terms from open encyclopaedic knowledge bases in four languages.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations