Re:Zero-shot transfer across 93 languages
by nograpes on Tuesday January 22, 2019 @05:05PM
(#18973053)
I think the English translations of the Hindi and the Bulgarian are mixed up. The Hindi should be "Their destination was secret", and the Bulgarian should be "Nobody knew where they went". Also, the Devnagari script is not rendered properly; the diacritical marks should be directly over (or under) the related character, and conjunct characters are not "squished" together.
[ Parent
| on HN ]
Re:Zero-shot transfer across 93 languages
by statguy on Wednesday January 23, 2019 @03:03AM
(#18976531)
Also the Hindi translation is very formal, hardly anyone speaks like that colloquially. Which, is understandable because the translation probably reflects the data trained on, but something to keep in mind.
Re:Zero-shot transfer across 93 languages
by dmurray on Tuesday January 22, 2019 @07:49PM
(#18974579)
There are also half a dozen typos in the third graphic (the one showing relationships between languages). Hopefully the sloppiness here isn't a reflection on the overall quality of the work.
Re:Zero-shot transfer across 93 languages
by thaumasiotes on Tuesday January 22, 2019 @06:33PM
(#18973944)
> The Hindi should be "Their destination was secret", and the Bulgarian should be "Nobody knew where they went".
Those aren't good translations of each other (barring a helpful context); to me, "their destination was secret" states that the goal was for nobody to know where they went (with a weak implication that the goal was achieved), whereas "nobody knew where they went" states that, in reality, nobody knew where they went (and says nothing about whether that was intentional).
Re:Zero-shot transfer across 93 languages
by yorwba on Wednesday January 23, 2019 @04:05AM
(#18976803)
> Those aren't good translations of each other
That's because they're not translations. The table in the article makes it pretty clear that they're arbitrary sentences that were classified as "related" based on their embedding vectors.