{
  "annotation_id": "d6b1b4c3-59d8-4695-b07c-624ec78912c7",
  "date_created": "2026-02-17T05:53:24.376000Z",
  "date_modified": "2026-02-17T05:53:24.376000Z",
  "file_hash": "58622e33c62179873854ffee8998b233c6f620ebe0f4b7d83bb412f314ad5d68",
  "private": false,
  "record": {
    "abstract": "Punctuation plays a critical role in resolving semantic and structural ambiguity in written language. Machine Translation (MT) systems are now widely applied across diverse domains and languages, including many low-resource settings. In this work, we focus on Marathi, a low- to middle-resource language. We introduce Vir\\=am, the first diagnostic benchmark for assessing punctuation robustness in English-to-Marathi machine translation, consisting of 54 manually curated, punctuation-ambiguous instances. We evaluate two primary strategies for enhancing reliability: a pipeline-based restore-then-translate approach and direct fine-tuned on punctuation-varied data. Our results demonstrate that specialized fine-tuned models and pipeline systems significantly improve translation quality over standard baselines on the Vir\\=am benchmark. Qualitative analysis reveals that the original model may result in wrong translations leading to wrong interpretations, while fine-tuned models significantly improve overall reliability. Furthermore, we find that current Large Language Models (LLMs) lag behind these task-specific approaches in preserving meaning for punctuation-ambiguous text, thus necessitating further research in this area.",
    "arxiv_id": "2601.09725",
    "authors": [
      "Kaustubh Shivshankar Shejole",
      "Sourabh Deoghare",
      "Pushpak Bhattacharyya"
    ],
    "categories": [
      "cs.CL"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "title": "Assessing and Improving Punctuation Robustness in English-Marathi Machine Translation",
    "url": "https://arxiv.org/abs/2601.09725",
    "version": "v2"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "d2d48594-4aa6-4024-bf47-1f9968ac91c2",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}