Does Multimodality Help Human and Machine for Translation and Image Captioning?

Recommended citation: @inproceedings{caglayan2016wmt, address = {Berlin, Germany}, author = {O. Caglayan and W. Aransa and Y. Wang and M. Masana and M. García-Martínez and F. Bougares and L. Barrault and J. van de Weijer}, booktitle = {First Conference on Machine Translation}, category = {ACTI}, month = {August}, project = {M2CR}, title = {Does Multimodality Help Human and Machine for Translation and Image Captioning?}, url = {https://loicbarrault.github.io/papers/caglayan_wmt2016.pdf}, year = {2016} } https://loicbarrault.github.io/papers/caglayan_wmt2016.pdf