Publikace na Matematicko-fyzikální fakulta |
2018
Abstrakt
This paper presents a case study in translating short image captions of the Visual Genome dataset from English into Hindi using out-of-domain data sets of varying size. We experiment with three NMT models: the shallow and deep sequence-to-sequence and the Transformer model as implemented in Marian toolkit.
Phrase-based Moses serves as the baseline. The results indicate that the Transformer model outperforms others in the large data setting in a number of automatic metrics and manual evaluation, and it also produces the fewest truncated sentences.
Transformer training is however very sensitive to the hyperparameters, so it requires more experimenting.