5 papers
BM25-Augmented Many-Shot Translation for Low-Resource North-Eastern Indian Languages
Aashish Dhawan, Christopher Driggers-Ellis, Dzmitry Kasinets +2
This paper describes the University of Florida Gators submission to the WMT26 Low-Resource Indic Language Translation shared task. We adapt the retrieval-augmented many-shot transl…
Retrieval-Augmented Long-Context Translation for Cultural Image Captioning: Gators submission for AmericasNLP 2026 shared task
Aashish Dhawan, Christopher Driggers-Ellis, Dzmitry Kasinets +2
We present the University of Florida Gators submission to the AmericasNLP 2026 shared task on cultural image captioning for Indigenous languages. Our two-stage pipeline generates a…
Semantic Similarity is a Spurious Measure of Comic Understanding: Lessons Learned from Hallucinations in a Benchmarking Experiment
Christopher Driggers-Ellis, Nachiketh Tibrewal, Rohit Bogulla +4
A system that enables blind or visually impaired users to access comics/manga would introduce a new medium of storytelling to this community. However, no such system currently exis…
Improving Indigenous Language Machine Translation with Synthetic Data and Language-Specific Preprocessing
Aashish Dhawan, Christopher Driggers-Ellis, Christan Grant +1
Low-resource indigenous languages often lack the parallel corpora required for effective neural machine translation (NMT). Synthetic data generation offers a practical strategy for…
MultiScript30k: Leveraging Multilingual Embeddings to Extend Cross Script Parallel Data
Christopher Driggers-Ellis, Detravious Brinkley, Ray Chen +3
Multi30k is frequently cited in the multimodal machine translation (MMT) literature, offering parallel text data for training and fine-tuning deep learning models. However, it is l…