arXiv Computation and Language September 18, 2026 By Ruiyan Sun, Satoshi Nakamura

Automated Gradient-Driven Parameter Sharing for Low-Resource Multilingual Speech-to-Text Translation

Read the original on arXiv Computation and Language →

The paper addresses low-resource multilingual speech-to-text translation, noting that uniform sharing of model layers across languages can cause representation conflicts that hinder convergence. It introduces a method that automatically identifies layer-specific sharing patterns by analyzing training gradients, using distance-based language clustering, self/cross-task divergence metrics, and joint factorization with canonical correlation analysis. Experiments on four language pairs with the SeamlessM4T-Medium architecture show consistent improvements in translation quality metrics.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

safety

arXiv AI

Aug 7

Breaking the Curse of Multilinguality in Many-to-Many Speech-to-Text Translation via a Resource-Aware Mixture of Speech Encoders

arXiv:2608. 04586v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) have achieved significant success in speech-to-text translation (S2TT).

By Yexing Du, Kaiyuan Liu, Youcheng Pan, Bo Yang, Chengpeng Fu, Yu Wang, Ming Liu

llms multimodal benchmarks safety

arXiv AI

Aug 6

Breaking the Curse ofMultilinguality inMany-to-Many Speech-to-Text Translation via a Resource-AwareMixture of Speech Encoders

arXiv:2608. 04586v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) have achieved significant success in speech-to-text translation (S2TT).

By Yexing Du, Kaiyuan Liu, Youcheng Pan, Bo Yang, Chengpeng Fu, Yu Wang, Ming Liu

llms multimodal benchmarks safety

arXiv AI

Sep 1

Transformer-Encoder Trees for Efficient Multilingual Machine Translation and Speech Translation

arXiv:2509.17930v3 Announce Type: replace-cross Abstract: Multilingual translation suffers from computational redundancy, especially when translating into multiple languages simultaneously. In additi...

By Yiwen Guan, Jacob Whitehill

llms nlp multimodal

arXiv Computation and Language

Aug 25

Predicting Multilingual Classification and Translation Performance of LLMs with Cross-Lingual Alignment -- Is English Enough?

arXiv:2608.03446v2 Announce Type: replace Abstract: Multilingual large language models (LLMs) have been shown to perform better on non-English classification tasks when the representations of the giv...

By Adnan Al Ali, Kathy H\"ammerl, Jind\v{r}ich Libovick\'y, Alexander Fraser

llms rag nlp safety

arXiv AI

Jun 2

Understanding LLM Behavior in Multi-Target Cross-Lingual Summarization

arXiv:2606. 01252v1 Announce Type: cross Abstract: Multi-target cross-lingual text summarization (MTXLS), which summarizes a source document into multiple target languages, is increasingly important as users consume content in diverse languages, but remains underexplored.

By Sangwon Ryu, Yihong Liu, Mingyang Wang, Yunsu Kim, Jungseul Ok, Gary Geunbae Lee, Hinrich Schuetze

llms nlp benchmarks

arXiv Computation and Language

Sep 25

EnSiTa - A Trilingual Multi-Domain Parallel Dataset and Benchmark for Domain-Specific Machine Translation

EnSiTa is a trilingual multi‑domain parallel dataset and benchmark for English, Sinhala, and Tamil. It contains human post‑edited training data across seven domains and professionally translated test sets for those domains plus an additional one, all produced through a multi‑year, rigorously quality‑controlled process. The authors use EnSiTa to conduct a comprehensive study of domain‑specific machine translation across six language directions, comparing from‑scratch Transformers, pre‑trained models, and decoder‑only LLMs under various training‑data sizes, model scales, and domain settings.

By Surangika Ranathunga, Nisansa de Silva, Aloka Fernando, Kavindu Warnakulasuriya, Isuru Wijesiri, Menan Velayuthan, Charitha Rathnayaka, Thivaharan Varatharajan, Sajeevi Silva, Piumi Kandanaarachchi, Uthayasanker Thayasivam

llms nlp fine-tuning benchmarks

One email a morning, machine-written

Related stories

Breaking the Curse of Multilinguality in Many-to-Many Speech-to-Text Translation via a Resource-Aware Mixture of Speech Encoders

Breaking the Curse ofMultilinguality inMany-to-Many Speech-to-Text Translation via a Resource-AwareMixture of Speech Encoders

Transformer-Encoder Trees for Efficient Multilingual Machine Translation and Speech Translation

Predicting Multilingual Classification and Translation Performance of LLMs with Cross-Lingual Alignment -- Is English Enough?

Understanding LLM Behavior in Multi-Target Cross-Lingual Summarization

EnSiTa - A Trilingual Multi-Domain Parallel Dataset and Benchmark for Domain-Specific Machine Translation