Using images to improve machine-translating
E-commerce product listings
Calixto, Iacer, Stein, Daniel, Matusov, Evgeny, Lohar, PintuORCID: 0000-0002-5328-1585, Castilho, SheilaORCID: 0000-0002-8416-6555 and Way, AndyORCID: 0000-0001-5736-5930
(2017)
Using images to improve machine-translating
E-commerce product listings.
In: 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2017), 3-7 April 2017, Valencia, Spain.
ISBN 978-1-945626-35-7
In this paper we study the impact of using
images to machine-translate user-generated ecommerce product listings. We study how
a multi-modal Neural Machine Translation
(NMT) model compares to two text-only approaches: a conventional state-of-the-art attentional NMT and a Statistical Machine Translation (SMT) model. User-generated product
listings often do not constitute grammatical
or well-formed sentences. More often than
not, they consist of the juxtaposition of short
phrases or keywords. We train our models
end-to-end as well as use text-only and multimodal NMT models for re-ranking n-best lists
generated by an SMT model. We qualitatively evaluate our user-generated training data
also analyse how adding synthetic data impacts the results. We evaluate our models
quantitatively using BLEU and TER and find
that (i) additional synthetic data has a general
positive impact on text-only and multi-modal
NMT models, and that (ii) using a multi-modal
NMT model for re-ranking n-best lists improves TER significantly across different nbest list sizes.
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers.
2.
Association for Computational Linguistics (ACL). ISBN 978-1-945626-35-7