We present the preliminary findings of the WAT 2025 shared task on document-level translation from Japanese to English in the news domain. This task focuses on translating full articles with particular attention to whether translation models can learn to produce expressions and stylistic features typical of English news writing, with the aim to generate outputs that resemble original English news articles. The task consists of three translation styles: (1) literal translation, (2) news-style translation, based on English articles edited to match Japanese content, and (3) finalized translation, the primary goal of this shared task. Only one team participated and submitted a system to a single subtask. All tasks were evaluated automatically, and one task was also evaluated manually to compare the submission with the baseline.

The repetition of words in an English sentence can create a monotonous or awkward impression. In such cases, repetition should be avoided appropriately. To evaluate the performance of machine translation (MT) systems in avoiding such repetition and outputting more polished translations, we presented the shared task of controlling the lexical choice of MT systems. From Japanese–English parallel news articles, we collected several hundred sentence pairs in which the source sentences containing repeated words were translated in a style that avoided repetition. Participants were required to encourage the MT system to output tokens in a non-repetitive manner while maintaining translation quality. We conducted human and automatic evaluations of systems submitted by two teams based on an encoder-decoder Transformer and a large language model, respectively. From the experimental results and analysis, we report a series of findings on this task.