Lessons learned in multilingual grounded language learning
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Standard
Lessons learned in multilingual grounded language learning. / Kádár, Ákos; Elliott, Desmond; Côté, Marc-Alexandre; Chrupala, Grzegorz; Alishahi, Afra.
Proceedings of the 22nd Conference on Computational Natural Language Learning. Association for Computational Linguistics, 2018. p. 402-412.Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Lessons learned in multilingual grounded language learning
AU - Kádár, Ákos
AU - Elliott, Desmond
AU - Côté, Marc-Alexandre
AU - Chrupala, Grzegorz
AU - Alishahi, Afra
PY - 2018
Y1 - 2018
N2 - Recent work has shown how to learn bettervisual-semantic embeddings by leveraging imagedescriptions in more than one language.Here, we investigate in detail which conditionsaffect the performance of this type of grounded language learning model. We show that multilingual training improves over bilingual training, and that low-resource languages benefit from training with higher-resource languages. We demonstrate that a multilingual model can be trained equally well on either translations or comparable sentence pairs, and that annotating the same set of images in multiple language enables further improvements via an additional caption-caption ranking objective
AB - Recent work has shown how to learn bettervisual-semantic embeddings by leveraging imagedescriptions in more than one language.Here, we investigate in detail which conditionsaffect the performance of this type of grounded language learning model. We show that multilingual training improves over bilingual training, and that low-resource languages benefit from training with higher-resource languages. We demonstrate that a multilingual model can be trained equally well on either translations or comparable sentence pairs, and that annotating the same set of images in multiple language enables further improvements via an additional caption-caption ranking objective
M3 - Article in proceedings
SN - 978-1-948087-72-8
SP - 402
EP - 412
BT - Proceedings of the 22nd Conference on Computational Natural Language Learning
PB - Association for Computational Linguistics
T2 - 22nd Conference on Computational Natural Language Learning (CoNLL 2018)
Y2 - 31 October 2018 through 1 November 2018
ER -
ID: 230797458