Newest papers

Towards English - Mizo Legal Machine Translation: Corpus Creation, Analysis, and Benchmarks

Telem Joyson Singh, Sanabam Boyshana, Sanasam Ranbir Singh, Priyankoo Sarmah · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.29943 · cited by 0 works (OpenAlex) · open-access PDF

Japanese

インドの裁判所の手続きは英語で行われているため、翻訳技術が制限されている言語のスピーカーはそれらに限られたアクセスを有しています。 私たちはインドの裁判所の判決の最初のMizoパラレルデータセットをインドで紹介しています。それはGauhati High Courtとインド最高裁判所からの13168文のカップルを含みます。プロのネイティブMizo翻訳者は完全な文書を翻訳しました;文のカップルは手動で並べられ、二人の独立したレビュー者が結果をチェックしました。私たちの研究は、英語の単語が非常に選択的に借りられていることを発見します:公式および法的用語はほとんど常に英語で保管されていますが、行動、状況、および結果などの日常用語は通常ネイティブM

Machine translation (Meta M2M100); the English original follows.

Abstract

Indian court proceedings are held in English, so speakers of languages with limited translation technology have limited access to them. We present the first English Mizo parallel dataset of Indian court judgments. It contains 13,168 sentence pairs from the Gauhati High Court and the Supreme Court of India. Professional native Mizo translators translated complete documents; sentence pairs were manually aligned, and two independent reviewers checked the results. Our study finds that English words are borrowed in a very selective way: official and legal terms are almost always kept in English, but words for everyday things like actions, situations, and results are usually expressed in native Mizo. Mizo diacritics are also used inconsistently across the corpus. When we fine tune the NLLB 200 1.3B model on our training data, it scores 27.47 BLEU on a balanced legal test set of 1,000 sentence pairs, an improvement of 7.16 BLEU over the base model. However, it still uses English words about three times more often than a human translator does.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Sentence, Supreme court, Computer science, Natural language processing, Set (abstract data type), Artificial intelligence

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange