Multimodal Machine Translation through Visuals and Speech

Research output: Contribution to journal › Journal article › Research › peer-review

Standard

Multimodal Machine Translation through Visuals and Speech. / Sulubacak, Umut; Caglayan, Ozan; Grönroos, Stig-Arne; Rouhe, Aku; Elliott, Desmond; Specia, Lucia; Tiedemann, Jörg.

In: Machine Translation, Vol. 34, 2020, p. 97–147.

Research output: Contribution to journal › Journal article › Research › peer-review

Harvard

Sulubacak, U, Caglayan, O, Grönroos, S-A, Rouhe, A, Elliott, D, Specia, L & Tiedemann, J 2020, 'Multimodal Machine Translation through Visuals and Speech', Machine Translation, vol. 34, pp. 97–147. https://doi.org/10.1007/s10590-020-09250-0

APA

Sulubacak, U., Caglayan, O., Grönroos, S-A., Rouhe, A., Elliott, D., Specia, L., & Tiedemann, J. (2020). Multimodal Machine Translation through Visuals and Speech. Machine Translation, 34, 97–147. https://doi.org/10.1007/s10590-020-09250-0

Vancouver

Sulubacak U, Caglayan O, Grönroos S-A, Rouhe A, Elliott D, Specia L et al. Multimodal Machine Translation through Visuals and Speech. Machine Translation. 2020;34:97–147. https://doi.org/10.1007/s10590-020-09250-0

Author

Sulubacak, Umut ; Caglayan, Ozan ; Grönroos, Stig-Arne ; Rouhe, Aku ; Elliott, Desmond ; Specia, Lucia ; Tiedemann, Jörg. / Multimodal Machine Translation through Visuals and Speech. In: Machine Translation. 2020 ; Vol. 34. pp. 97–147.

Bibtex

@article{4d822977ad9748649af78593bc30e0a4,
title = "Multimodal Machine Translation through Visuals and Speech",
abstract = " Multimodal machine translation involves drawing information from more than one modality, based on the assumption that the additional modalities will contain useful alternative views of the input data. The most prominent tasks in this area are spoken language translation, image-guided translation, and video-guided translation, which exploit audio and visual modalities, respectively. These tasks are distinguished from their monolingual counterparts of speech recognition, image captioning, and video captioning by the requirement of models to generate outputs in a different language. This survey reviews the major data resources for these tasks, the evaluation campaigns concentrated around them, the state of the art in end-to-end and pipeline approaches, and also the challenges in performance evaluation. The paper concludes with a discussion of directions for future research in these areas: the need for more expansive and challenging datasets, for targeted evaluations of model performance, and for multimodality in both the input and output space. ",
author = "Umut Sulubacak and Ozan Caglayan and Stig-Arne Gr{\"o}nroos and Aku Rouhe and Desmond Elliott and Lucia Specia and J{\"o}rg Tiedemann",
year = "2020",
doi = "10.1007/s10590-020-09250-0",
language = "English",
volume = "34",
pages = "97–147",
journal = "Machine Translation",
issn = "0922-6567",
publisher = "Springer",

}

RIS

TY - JOUR

T1 - Multimodal Machine Translation through Visuals and Speech

AU - Sulubacak, Umut

AU - Caglayan, Ozan

AU - Grönroos, Stig-Arne

AU - Rouhe, Aku

AU - Elliott, Desmond

AU - Specia, Lucia

AU - Tiedemann, Jörg

PY - 2020

Y1 - 2020

N2 - Multimodal machine translation involves drawing information from more than one modality, based on the assumption that the additional modalities will contain useful alternative views of the input data. The most prominent tasks in this area are spoken language translation, image-guided translation, and video-guided translation, which exploit audio and visual modalities, respectively. These tasks are distinguished from their monolingual counterparts of speech recognition, image captioning, and video captioning by the requirement of models to generate outputs in a different language. This survey reviews the major data resources for these tasks, the evaluation campaigns concentrated around them, the state of the art in end-to-end and pipeline approaches, and also the challenges in performance evaluation. The paper concludes with a discussion of directions for future research in these areas: the need for more expansive and challenging datasets, for targeted evaluations of model performance, and for multimodality in both the input and output space.

AB - Multimodal machine translation involves drawing information from more than one modality, based on the assumption that the additional modalities will contain useful alternative views of the input data. The most prominent tasks in this area are spoken language translation, image-guided translation, and video-guided translation, which exploit audio and visual modalities, respectively. These tasks are distinguished from their monolingual counterparts of speech recognition, image captioning, and video captioning by the requirement of models to generate outputs in a different language. This survey reviews the major data resources for these tasks, the evaluation campaigns concentrated around them, the state of the art in end-to-end and pipeline approaches, and also the challenges in performance evaluation. The paper concludes with a discussion of directions for future research in these areas: the need for more expansive and challenging datasets, for targeted evaluations of model performance, and for multimodality in both the input and output space.

U2 - 10.1007/s10590-020-09250-0

DO - 10.1007/s10590-020-09250-0

M3 - Journal article

VL - 34

SP - 97

EP - 147

JO - Machine Translation

JF - Machine Translation

SN - 0922-6567

ER -

ID: 256481243