• Home
  • Blog
  • People
  • Projects
  • Publications
  • Seminars
  • DSR Expo
  • Courses
logo1

Data Science Research

Menu
  • Home
  • Blog
  • People
  • Projects
  • Publications
  • Seminars
  • DSR Expo
  • Courses
Home  ›  Uncategorized  ›  DBSim: Extensible Database Simulator for Fast Prototyping In-Database Algorithms

Team Gators Wins the AmericasNLP 2026 Shared Task on Indigenous Language Image Captioning

Aashish Dhawan May 13, 2026     Comment Closed     Uncategorized

by Aashish Dhawan


A UF Data Science Research Lab and Data Studio Lab collaboration placed second in all five language tracks — earning the highest overall score through consistent performance across Guaraní, Yucatec Maya, Nahuatl, Wixarika, and Bribri.

Winning the Overall Competition
Team Gators, a collaboration between the UF Data Science Research Lab and the UF Data Studio Lab, won the overall AmericasNLP 2026 Shared Task on Cultural Image Captioning for Indigenous Languages, co-located with ACL 2026 in San Diego. The task asked participating systems to generate captions for culturally situated images in five Indigenous languages: Guaraní, Yucatec Maya, Orizaba Nahuatl, Wixarika, and Bribri. Evaluation used a two-stage process: systems were first ranked by chrF++, a character n-gram metric standard in low-resource translation, and top systems then advanced to human evaluation on a 1–5 scale. The official overall winner was determined by summing rank points across all five languages — rewarding consistency rather than peak performance in a single track. Team Gators placed second in every language track, accumulating 20 points against 14 for NAIST and 13 each for Mila and yaduha.

img2
img2
img2

System Design: A Two-Stage Cascade
Rather than attempting to build a single end-to-end image-to-Indigenous-language model — which would require data that does not exist — Team Gators decomposed the problem into two stages. Stage 1 uses Qwen2.5-VL-72B-Instruct (4-bit quantized) on UF HiPerGator B200 GPUs to generate a Spanish description of each image. Spanish serves as a high-resource intermediate language. The caption prompt was designed to produce culturally specific vocabulary — naming objects like guampa, kambuchi, poyvi, and chipa by their local names rather than generic Spanish equivalents, since these terms match the vocabulary of the parallel training corpus and drive precise retrieval. Stage 2 uses Gemini 2.5 Flash (temperature 0.0) with BM25 retrieval-augmented in-context learning. For each image, the prompt combines: (a) gold development-set caption pairs as demonstrations (leave-one-out, 20–49 examples); and (b) BM25-retrieved parallel training examples (0–80 examples). Parameters r (retrieval size) and d (dev examples) were tuned independently for each language.

Key Findings
The base AmericasNLP 2023 Guaraní corpus contains ~26,000 sentence pairs. Earlier DSR Lab work augmented this to 53,000 pairs through NLLB back-translation. Removing the augmentation reveals a dramatic effect: without synthetic data, all configurations cluster near 21 chrF++ regardless of r or d. With augmentation, the best configuration (r=40, d=49) reaches 51.34 — a +30 point gain. The synthetic data improves retrieval quality, not the translation model itself, by adding caption-style Spanish vocabulary to the BM25 index.

img2

Retrieval must be tuned per language
The optimal retrieval configuration varied substantially across languages. For Guaraní (large augmented corpus), r=40 retrieved examples were highly beneficial. For Yucatec Maya, which had almost no parallel training data, r=0 was optimal — any retrieval from an out-of-domain corpus added noise. The principle: retrieval helps in proportion to corpus relevance, not corpus existence. Unicode encoding was silently suppressing Bribri scores
Bribri reference files use NFD Unicode encoding (decomposed diacritics) while our pipeline generated NFC text (precomposed). Since chrF++ is character-level, visually identical characters in different encodings score as mismatches. After NFD-normalizing predictions, the Bribri dev score jumped from 11.50 to 17.02 — points lost entirely to a file encoding artifact. Combined with a stronger language-specific system prompt, the final Bribri dev score reached 19.99.

img2

Links and Code
Team Repository: github.com/dhawan98/AmericasNLP2026-Gators-Submission
fficial Results: github.com/AmericasNLP/americasnlp2026/tree/main/results
Task Page: americasnlp.org

Uncategorized

 Previous Post

Improving Rare Tree Species Classification using Domain Knowledge

― Octorber 14, 2023

Related Articles

DrugEHRQA: A Question Answering Dataset on Structured and Unstructured Electronic Health Records For Medicine Related Queries
A Brief Overview of Weak Supervision
DRUM: End-To-End Differentiable Rule Mining On Knowledge Graphs
IDTrees Data Science Challenge: 2017
Efficient Conditional Rule Mining over Knowledge Bases

Recent Posts

  • DBSim: Extensible Database Simulator for Fast Prototyping In-Database Algorithms
  • DrugEHRQA: A Question Answering Dataset on Structured and Unstructured Electronic Health Records For Medicine Related Queries
  • A Brief Overview of Weak Supervision
  • DRUM: End-To-End Differentiable Rule Mining On Knowledge Graphs
  • IDTrees Data Science Challenge: 2017