Skip to main content

Resultados relacionados

Resultados totales (Incluyendo duplicados): 2
Encontrada(s) 1 página(s)

RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Speech Translation for Multilingual Medical Education Leveraged by Large Language Models

  • Iranzo-Sánchez, Jorge
  • Santamaría-Jordá, Jaume
  • Mas-Mollà, Gerard
  • Garcés Díaz-Munío, Gonçal|||0000-0002-2594-5858
  • Jorge-Cano, Javier|||0000-0002-9279-6768
  • Silvestre Cerdà, Joan Albert|||0000-0003-2291-8296
  • Giménez Pastor, Adrián
  • Civera Saiz, Jorge|||0000-0002-0963-0143
  • Sanchis Navarro, José Alberto|||0000-0002-2943-0990
  • Juan, Alfons|||0000-0002-9984-4072
  • Iranzo-Sánchez, Javier
[EN] The application of large language models (LLMs) to speech translation (ST) or, in general, to machine translation (MT) has recently provided excellent results, superseding conventional encoder-decoder MT systems in the general domain. However, this is not clearly the case when LLMs as MT systems are translating medical-related materials. In this respect, the provision of multilingual training materials for oncology professionals is a goal of the EU project Interact-Europe in which this work was framed. To this end, cross-language technology adapted to the oncology domain was developed, evaluated and deployed for multilingual interspecialty medical education. More precisely, automatic speech recognition (ASR) and MT models were adapted to the oncology domain to translate English pre-recorded training videos, kindly provided by the European School of Oncology (ESO), into French, Spanish, German and Slovene. In this work, three categories of MT models adapted to the medical domain were assessed: bilingual encoder-decoder MT models trained from scratch, pre-trained large multilingual encoder-decoder MT models, and multilingual decoder-only LLMs. The experimental results underline the competitiveness in translation quality of LLMs compared to encoder-decoder MT models. Finally, the ESO speech dataset, comprising roughly 1000 videos and 745 h for the training and evaluation of ASR, MT and ST models, was publicly released for the scientific community., The research leading to these results has received funding from EU4Health Programme 2021-2027 as part of Europe's Beating Cancer Plan under Grant Agreements nos. 101056995 and 101129375; and from the Government of Spain's grant PID2021-122443OB-I00 funded by MCIN/AEI/10.13039/5011-00011033 and by "ERDF Away of making Europe", and grant PDC2022-133049-I00 funded by MCIN/AEI/10.13039/501100011033 and by the "European Union NextGenerationEU/PRTR". The authors gratefully acknowledge the financial support of Generalitat Valenciana, Spain under project IDIFEDER/2021/059.The authors gratefully thank the EuropeanSchoolofOncology for the provision of this dataset in the framework of the EUresearchprojectInteract-Europe.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Segmentation-Free Streaming Machine Translation

  • Iranzo-Sánchez, Javier
  • Giménez, Adria
  • Iranzo-Sánchez, Jorge
  • Civera Saiz, Jorge|||0000-0002-0963-0143
  • Juan, Alfons|||0000-0002-9984-4072
[EN] Streaming Machine Translation (MT) is the task of translating an unbounded input text stream in real-time. The traditional cascade approach, which combines an Automatic Speech Recognition (ASR) and an MT system, relies on an intermediate segmentation step which splits the transcription stream into sentence-like units. However, the incorporation of a hard segmentation constrains the MT system and is a source of errors. This paper proposes a Segmentation-Free framework that enables the model to translate an unsegmented source stream by delaying the segmentation decision until after the translation has been generated. Extensive experiments show how the proposed Segmentation-Free framework has better quality-latency trade-off than competing approaches that use an independent segmentation model.1, We thank our action editor and the anonymous reviewers for their helpful and constructive comments on the paper. The research leading to these results has received funding from European Union's Horizon 2020 research and innovation program under grant agreement no. 952215 and EU4Health Programme 2021-2027 as part of Europe's Beating Cancer Plan under grant agreements nos. 101056995 and 101129375; and from the Government of Spain's grant PID2021-122443OB-I00 funded by MCIN/AEI/10.13039/501100011033 and by ''ERDF A way of making Europe'', grant PDC2022-133049-I00 funded by MCIN/AEI/10.13039/501100011033 and by the ''European Union NextGenerationEU/PRTR'' and FPU scholarship FPU18/04135. The authors gratefully acknowledge the financial support of the Generalitat Valenciana under project IDIFEDER/2021/059.