{"ID":2867794,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.17930","arxiv_id":"2509.17930","title":"Transformer-Encoder Trees for Efficient Multilingual Machine Translation and Speech Translation","abstract":"Multilingual translation suffers from computational redundancy, especially when translating into multiple languages simultaneously. In addition, translation quality can suffer for low-resource languages. To address this, we introduce Transformer Encoder Tree (TET), a hierarchical, non-autoregressive encoder-only architecture trained with Connectionist Temporal Classification (CTC) for multilingual translation. TET shares intermediate representations among linguistically similar target languages, improving accuracy on low-resource languages while reducing computational redundancy and enabling the generation of all target languages in a single forward pass. TET eliminates the sequential bottleneck of autoregressive models and supports fully parallel decoding of all tokens across all target languages. Compared to a naive one-to-many multilingual design, TET reduces the total parameter count by 66% and lowers inference computation by 60%. In speech translation, combining TET with a non-autoregressive speech recognition backbone (Wav2Vec2) shows competitive translation quality compared to autoregressive systems while speeding up inference by approximately 7-14 times.","short_abstract":"Multilingual translation suffers from computational redundancy, especially when translating into multiple languages simultaneously. In addition, translation quality can suffer for low-resource languages. To address this, we introduce Transformer Encoder Tree (TET), a hierarchical, non-autoregressive encoder-only archit...","url_abs":"https://arxiv.org/abs/2509.17930","url_pdf":"https://arxiv.org/pdf/2509.17930v2","authors":"[\"Yiwen Guan\",\"Jacob Whitehill\"]","published":"2025-09-22T15:52:18Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\"]","methods":"[\"Transformer\"]","has_code":false}