@inproceedings{betala-etal-2025-picture,
    title = "A Picture is Worth a Thousand (Correct) Captions: A Vision-Guided Judge-Corrector System for Multimodal Machine Translation",
    author = "Betala, Siddharth  and
      Raj, Kushan  and
      Betala, Vipul  and
      Saswade, Rohan",
    editor = "Nakazawa, Toshiaki  and
      Goto, Isao",
    booktitle = "Proceedings of the Twelfth Workshop on Asian Translation (WAT 2025)",
    month = dec,
    year = "2025",
    address = "Mumbai, India",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-ijcnlp-aacl/2025.wat-1.13/",
    pages = "124--137",
    ISBN = "979-8-89176-309-8",
    abstract = "In this paper, we describe our system under the team name BLEU Monday for the English-to-Indic Multimodal Translation Task at WAT 2025. We participate in the text-only translation tasks for English-Hindi, English-Bengali, English-Malayalam, and English-Odia language pairs. We present a two-stage approach that addresses quality issues in the training data through automated error detection and correction, followed by parameter-efficient model fine-tuning.Our methodology introduces a vision-augmented judge-corrector pipeline that leverages multimodal language models to systematically identify and correct translation errors in the training data. The judge component classifies translations into three categories: correct, visually ambiguous (requiring image context), or mistranslated (poor translation quality). Identified errors are routed to specialized correctors: GPT-4o-mini regenerates captions requiring visual disambiguation, while IndicTrans2 retranslates cases with pure translation quality issues. This automated pipeline processes 28,928 training examples across four languages, correcting an average of 17.1{\%} of captions per language.We then apply Low-Rank Adaptation (LoRA) to fine-tune the IndicTrans2 en-indic 200M distilled model on both original and corrected datasets. Training on corrected data yields consistent improvements, with BLEU score gains of +1.30 for English-Bengali on the evaluation set (42.00 {\textrightarrow} 43.30) and +0.70 on the challenge set (44.90 {\textrightarrow} 45.60), +0.60 for English-Odia on the evaluation set (41.00 {\textrightarrow} 41.60), and +0.10 for English-Hindi on the challenge set (53.90 {\textrightarrow} 54.00)."
}