Multimodal quality estimation for machine translation

Shu Okabe; Frédéric Blain; Lucia Specia

doi:10.18653/v1/2020.acl-main.114

Multimodal quality estimation for machine translation

Shu Okabe, Frédéric Blain, Lucia Specia

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

Original language	English
Title of host publication	Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL)
Publisher	Association for Computational Linguistics
DOIs	https://doi.org/10.18653/v1/2020.acl-main.114
Publication status	Published - 2020
Externally published	Yes

Access to Document

10.18653/v1/2020.acl-main.114

http://hdl.handle.net/2436/623554

Cite this

@inproceedings{4d7768a7834d4f578c8b866f47d70fd6,

title = "Multimodal quality estimation for machine translation",

author = "Shu Okabe and Fr{\'e}d{\'e}ric Blain and Lucia Specia",

note = "We propose approaches to Quality Estimation (QE) for Machine Translation that explore both text and visual modalities for Multimodal QE. We compare various multimodality integration and fusion strategies. For both sentence-level and document-level predictions, we show that state-of-the-art neural and feature-based QE frameworks obtain better results when using the additional modality.",

year = "2020",

doi = "10.18653/v1/2020.acl-main.114",

language = "English",

booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL)",

publisher = "Association for Computational Linguistics",

}

TY - GEN

T1 - Multimodal quality estimation for machine translation

AU - Okabe, Shu

AU - Blain, Frédéric

AU - Specia, Lucia

N1 - We propose approaches to Quality Estimation (QE) for Machine Translation that explore both text and visual modalities for Multimodal QE. We compare various multimodality integration and fusion strategies. For both sentence-level and document-level predictions, we show that state-of-the-art neural and feature-based QE frameworks obtain better results when using the additional modality.

PY - 2020

Y1 - 2020

U2 - 10.18653/v1/2020.acl-main.114

DO - 10.18653/v1/2020.acl-main.114

M3 - Conference contribution

BT - Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL)

PB - Association for Computational Linguistics

ER -