43 citations · 85 across the 19 of their papers we have counts for
19 papers
SpanCalib-VLM: Calibrated Hallucination Span Detection in Vision-Language Models
Amanuel Gizachew Abebe, Yasmin Moslem
Detecting hallucinations in Large Vision-Language Models (LVLMs) requires both accurate span localization and well-calibrated confidence scores. Fine-tuned generative VLMs excel at…
Cluster, Route, Escalate: Cascaded Framework for Cost-Aware LLM Serving
Yasmin Moslem, Magdalena Kacmajor, Vasudevan Nedumpozhimana +11
Serving open-weight language models on premises forces a trade-off between accuracy and computational cost. Hosting models of different sizes lets easy queries go to a small, effic…
One Voice, Many Tongues: Cross-Lingual Voice Cloning for Scientific Speech
Amanuel Gizachew Abebe, Yasmin Moslem
Preserving a speaker's voice identity while generating speech in a different language remains a fundamental challenge in spoken language technology, particularly in specialized dom…
Dynamic Model Routing and Cascading for Efficient LLM Inference: A Survey
Yasmin Moslem, John D. Kelleher
The rapid growth of large language models (LLMs) with diverse capabilities, costs, and domains has created a critical need for intelligent model selection at inference time. While…
AfriNLLB: Efficient Translation Models for African Languages
Yasmin Moslem, Aman Kassahun Wassie, Amanuel Gizachew Abebe
In this work, we present AfriNLLB, a series of lightweight models for efficient translation from and into African languages. AfriNLLB supports 15 language pairs (30 translation dir…
Iterative Layer Pruning for Efficient Translation Inference
Yasmin Moslem, Muhammad Hazim Al Farouq, John D. Kelleher
Large language models (LLMs) have transformed many areas of natural language processing, including machine translation. However, efficient deployment of LLMs remains challenging du…
Efficient Speech Translation through Model Compression and Knowledge Distillation
Yasmin Moslem
Efficient deployment of large audio-language models for speech translation remains challenging due to their significant computational requirements. In this paper, we address this c…
Bemba Speech Translation: Exploring a Low-Resource African Language
Muhammad Hazim Al Farouq, Aman Kassahun Wassie, Yasmin Moslem
This paper describes our system submission to the International Conference on Spoken Language Translation (IWSLT 2025), low-resource languages track, namely for Bemba-to-English sp…
SpeechT: Findings of the First Mentorship in Speech Translation
Yasmin Moslem, Juan Julián Cea Morán, Mariano Gonzalez-Gomez +3
This work presents the details and findings of the first mentorship in speech translation (SpeechT), which took place in December 2024 and January 2025. To fulfil the mentorship re…
Domain-Specific Translation with Open-Source Large Language Models: Resource-Oriented Analysis
Aman Kassahun Wassie, Mahdi Molaei, Yasmin Moslem
In this work, we compare the domain-specific translation performance of open-source autoregressive decoder-only large language models (LLMs) with task-oriented machine translation…
Leveraging Synthetic Audio Data for End-to-End Low-Resource Speech Translation
Yasmin Moslem
This paper describes our system submission to the International Conference on Spoken Language Translation (IWSLT 2024) for Irish-to-English speech translation. We built end-to-end…
SEACrowd: A Multilingual Multimodal Data Hub and Benchmark Suite for Southeast Asian Languages
Holy Lovenia, Rahmad Mahendra, Salsabil Maulana Akbar +58
Southeast Asia (SEA) is a region rich in linguistic diversity and cultural variety, with over 1,300 indigenous languages and a population of 671 million people. However, prevailing…
Language Modelling Approaches to Adaptive Machine Translation
Yasmin Moslem
Consistency is a key requirement of high-quality translation. It is especially important to adhere to pre-approved terminology and adapt to corrected translations in domain-specifi…
Fine-tuning Large Language Models for Adaptive Machine Translation
Yasmin Moslem, Rejwanul Haque, Andy Way
This paper presents the outcomes of fine-tuning Mistral 7B, a general-purpose large language model (LLM), for adaptive machine translation (MT). The fine-tuning process involves ut…
Domain Terminology Integration into Machine Translation: Leveraging Large Language Models
Yasmin Moslem, Gianfranco Romani, Mahdi Molaei +3
This paper discusses the methods that we used for our submissions to the WMT 2023 Terminology Shared Task for German-to-English (DE-EN), English-to-Czech (EN-CS), and Chinese-to-En…
Adaptive Machine Translation with Large Language Models
Yasmin Moslem, Rejwanul Haque, John D. Kelleher +1
Consistency is a key requirement of high-quality translation. It is especially important to adhere to pre-approved terminology and adapt to corrected translations in domain-specifi…
Translation Word-Level Auto-Completion: What can we achieve out of the box?
Yasmin Moslem, Rejwanul Haque, Andy Way
Research on Machine Translation (MT) has achieved important breakthroughs in several areas. While there is much more to be done in order to build on this success, we believe that t…
Domain-Specific Text Generation for Machine Translation
Yasmin Moslem, Rejwanul Haque, John D. Kelleher +1
Preservation of domain knowledge from the source to target is crucial in any translation workflow. It is common in the translation industry to receive highly specialized projects,…
Preparing an Endangered Language for the Digital Age: The Case of Judeo-Spanish
Alp Öktem, Rodolfo Zevallos, Yasmin Moslem +2
We develop machine translation and speech synthesis systems to complement the efforts of revitalizing Judeo-Spanish, the exiled language of Sephardic Jews, which survived for centu…