Investigating 'Aspect' in NMT and SMT: translating the English simple past and present perfect
Vanmassenhove, EvaORCID: 0000-0003-1162-820X, Du, JinhuaORCID: 0000-0002-3267-4881 and Way, AndyORCID: 0000-0001-5736-5930
(2017)
Investigating 'Aspect' in NMT and SMT: translating the English simple past and present perfect.
Computational Linguistics in the Netherlands Journal (CLIN), 7
.
pp. 109-128.
ISSN 2211-4009
One of the important differences between English and French grammar is related to
how their verbal systems handle aspectual information. While the English simple past tense
is aspectually neutral, the French and Spanish past tenses are linked with a particular
imperfective/perfective aspect. This study examines what Statistical Machine Translation
(SMT) and Neural Machine Translation (NMT) learn about 'aspect'and how this is reflected in
the translations they produce. We use their main knowledge sources, phrase-tables (SMT)
and encoding vectors (NMT), to examine what kind of aspectual information they encode.
Furthermore, we examine whether this encoded 'knowledge'is actually transferred during
decoding and thus reflected in the actual translations. Our study is based on the translations
of the English simple past and present perfect tenses into French and Spanish …