Towards cross-cultural machine translation with retrieval-augmented generation from multilingual knowledge graphs

S Conia, D Lee, M Li, UF Minhas, S Potdar… - arXiv preprint arXiv …, 2024 - arxiv.org
Translating text that contains entity names is a challenging task, as cultural-related
references can vary significantly across languages. These variations may also be caused by …

Multilingual text-to-image generation magnifies gender stereotypes and prompt engineering may not help you

F Friedrich, K Hämmerl, P Schramowski… - arXiv preprint arXiv …, 2024 - arxiv.org
Text-to-image generation models have recently achieved astonishing results in image
quality, flexibility, and text alignment, and are consequently employed in a fast-growing …

Findings of the WMT 2024 Shared Task Translation into Low-Resource Languages of Spain: Blending Rule-Based and Neural Systems

F Sánchez‐Martínez, JA Pérez-Ortiz… - Proceedings of the …, 2024 - aclanthology.org
This paper presents the results of the Ninth Conference on Machine Translation (WMT24)
Shared Task “Translation into Low-Resource Languages of Spain”'. The task focused on the …

Defending text-to-image diffusion models: Surprising efficacy of textual perturbations against backdoor attacks

O Chew, PY Lu, J Lin, HT Lin - arXiv preprint arXiv:2408.15721, 2024 - arxiv.org
Text-to-image diffusion models have been widely adopted in real-world applications due to
their ability to generate realistic images from textual descriptions. However, recent studies …

[HTML][HTML] Transformer-Based Re-Ranking Model for Enhancing Contextual and Syntactic Translation in Low-Resource Neural Machine Translation

A Javed, H Zan, O Mamyrbayev, M Abdullah, K Ahmed… - Electronics, 2025 - mdpi.com
Neural machine translation (NMT) plays a vital role in modern communication by bridging
language barriers and enabling effective information exchange across diverse linguistic …

PyMarian: Fast Neural Machine Translation and Evaluation in Python

T Gowda, R Grundkiewicz, E Rippeth, M Post… - arXiv preprint arXiv …, 2024 - arxiv.org
The deep learning language of choice these days is Python; measured by factors such as
available libraries and technical support, it is hard to beat. At the same time, software written …

Analyzing the Attention Heads for Pronoun Disambiguation in Context-aware Machine Translation Models

P Mąka, YC Semerci, J Scholtes… - arXiv preprint arXiv …, 2024 - arxiv.org
In this paper, we investigate the role of attention heads in Context-aware Machine
Translation models for pronoun disambiguation in the English-to-German and English-to …

Improving Language Models Trained with Translated Data via Continual Pre-Training and Dictionary Learning Analysis

S Boughorbel, MD Parvez, M Hawasly - arXiv preprint arXiv:2405.14277, 2024 - arxiv.org
Training LLMs in low resources languages usually utilizes data augmentation with machine
translation (MT) from English language. However, translation brings a number of challenges …

Automated Medical Report Generation for ECG Data: Bridging Medical Text and Signal Processing with Deep Learning

A Bleich, A Linnemann, BH Diem… - arXiv preprint arXiv …, 2024 - arxiv.org
Recent advances in deep learning and natural language generation have significantly
improved image captioning, enabling automated, human-like descriptions for visual content …

Enabling Low-Resource Language Retrieval: Establishing Baselines for Urdu MS MARCO

U Butt, S Veranasi, G Neumann - arXiv preprint arXiv:2412.12997, 2024 - arxiv.org
As the Information Retrieval (IR) field increasingly recognizes the importance of inclusivity,
addressing the needs of low-resource languages remains a significant challenge. This …