Assessing multilingual multimodal image description: Studies of native speaker preferences and translator choices

Stella Frank, Desmond Elliott, Lucia Specia

Research output: Contribution to journalArticlepeer-review

Abstract

Two studies on multilingual multimodal image description provide empirical evidence towards two hypotheses at the core of the task: (i) whether target language speakers pre- fer descriptions generated directly in their native language, as compared to descriptions translated from a different language; (ii) the role of the image in human translation of de- scriptions. These results provide guidance for future work in multimodal natural language processing by firstly showing that on the whole, translations are not distinguished from native language descriptions, and secondly delineating and quantifying the information gained from the image during the human translation task.
Original languageEnglish
Pages (from-to)393-413
JournalNatural Language Engineering
Volume24
Issue number3
Early online date23 Apr 2018
DOIs
Publication statusPublished - May 2018

Fingerprint Dive into the research topics of 'Assessing multilingual multimodal image description: Studies of native speaker preferences and translator choices'. Together they form a unique fingerprint.

Cite this