Pith. sign in

REVIEW

Cross-modal Language Generation using Pivot Stabilization for Web-scale Language Coverage

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2005.00246 v1 pith:7VCOGNUD submitted 2020-05-01 cs.CL cs.CVcs.LG

Cross-modal Language Generation using Pivot Stabilization for Web-scale Language Coverage

classification cs.CL cs.CVcs.LG
keywords englishlanguageannotationsgenerationmodelsplugssolutionscaption
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Cross-modal language generation tasks such as image captioning are directly hurt in their ability to support non-English languages by the trend of data-hungry models combined with the lack of non-English annotations. We investigate potential solutions for combining existing language-generation annotations in English with translation capabilities in order to create solutions at web-scale in both domain and language coverage. We describe an approach called Pivot-Language Generation Stabilization (PLuGS), which leverages directly at training time both existing English annotations (gold data) as well as their machine-translated versions (silver data); at run-time, it generates first an English caption and then a corresponding target-language caption. We show that PLuGS models outperform other candidate solutions in evaluations performed over 5 different target languages, under a large-domain testset using images from the Open Images dataset. Furthermore, we find an interesting effect where the English captions generated by the PLuGS models are better than the captions generated by the original, monolingual English model.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.