Cross-linguistic differences and similarities in image descriptions

07/06/2017
by   Emiel van Miltenburg, et al.
0

Automatic image description systems are commonly trained and evaluated on large image description datasets. Recently, researchers have started to collect such datasets for languages other than English. An unexplored question is how different these datasets are from English and, if there are any differences, what causes them to differ. This paper provides a cross-linguistic comparison of Dutch, English, and German image descriptions. We find that these descriptions are similar in many respects, but the familiarity of crowd workers with the subjects of the images has a noticeable influence on description specificity.

READ FULL TEXT

page 6

page 7

research
05/02/2016

Multi30K: Multilingual English-German Image Descriptions

We introduce the Multi30K dataset to stimulate multilingual multimodal r...
research
08/10/2018

Homophonic Quotients of Linguistic Free Groups: German, Korean, and Turkish

In 1993, the homophonic quotient groups for French and English (the quot...
research
09/27/2022

Strategyproofness-Exposing Mechanism Descriptions

A menu description defines a mechanism to player i in two steps. Step (1...
research
07/24/2017

Image Pivoting for Learning Multilingual Multimodal Representations

In this paper we propose a model to learn multimodal multilingual repres...
research
04/26/2017

Punny Captions: Witty Wordplay in Image Descriptions

Wit is a quintessential form of rich inter-human interaction, and is oft...
research
04/13/2017

Room for improvement in automatic image description: an error analysis

In recent years we have seen rapid and significant progress in automatic...
research
03/25/2022

AUTOLEX: An Automatic Framework for Linguistic Exploration

Each language has its own complex systems of word, phrase, and sentence ...

Please sign up or login with your details

Forgot password? Click here to reset