Papers by Vera Pavlova
MOSAIC: Masked Objective with Selective Adaptation for In-domain Contrastive Learning (2026.findings-eacl)
Copied to clipboard
| Challenge: | a new framework for domain adaptation of text embedding models addresses the challenges of adapting general-domain text embeds to specialized domains. |
| Approach: | They propose a framework for domain adaptation of text embedding models that integrates masked supervision and mangled objectives within a unified training pipeline. |
| Outcome: | The proposed framework improves on high-resource and low-resourced domains while preserving the robustness of the original model. |
Efficient and Versatile Model for Multilingual Information Retrieval of Islamic Text: Development and Deployment in Real-World Scenarios (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Despite recent advances in multilingual information retrieval, a significant gap remains between research efforts and real-world deployment. |
| Approach: | They propose to use Quranic multilingual corpus to develop an ad-hoc IR system that can satisfy users’ information needs in multiple languages. |
| Outcome: | The proposed model achieves promising results across diverse retrieval scenarios. |
Building an Efficient Multilingual Non-Profit IR System for the Islamic Domain Leveraging Multiprocessing Design in Rust (2024.emnlp-industry)
Copied to clipboard
| Challenge: | Existing models that are pre-trained on a general domain can deteriorate performance due to domain shift when applied to new domains. |
| Approach: | They propose to train a multilingual non-profit IR system for the Islamic domain using Rust Language capabilities. |
| Outcome: | The proposed model outperforms models pre-trained on general domains and on resource-constrained devices. |