Computers have been teaching themselves to
translate text for some time now,
but most methods are concerned with
translations on entire sentences.
We address the problem of simultaneous
machine translation for distant
language pairs: from verb-final (SOV) to verb-medial
(SVO) languages.
Simultaneous translation is the process of translating
before a sentence
is complete. When humans do this, it is
called simultaneous interpretation.
Much of the prior work in this area has focused on using
rule-based approaches.
We use machine learning to allow the system to teach
itself how to
create better simultaneous translations.
Learn to
Translate Incrementally
We do not program translation strategies into the
system.
Instead, we provide our imitation learning system with
features.
On the basis of these features, the system decides when
and if
to translate sections of a sentence. Does it WAIT
for more words
or COMMIT to a partial translation?
We use imitation learning to allow the system to produce
better
simultaneous translations on the basis of its
features. The focus
is then shifted to better features, not programming
complex strategies.
Every time the system makes a decision, it compares it to
the optimal
decision that it could have made. In this
way, the system
learns from its mistakes and its successes, much in the
same way
a professional simultaneous interpreter would.
Predict the
Future
Some languages, such as German and Japanese, have
verb-final
constructions, in which the main verb appears at the end of
the sentence.
How does one translate something that hasn't yet been
spoken?
One way is to guess what the speaker will say based on
what the
speaker has already said. We integrate a verb
prediction component
to allow for translation from SOV to SVO languages.
Through reinforcement learning, the system learns when
to
trust these predictions.
A Cumulative Metric
BLEU has been the
standard metric for most languages in machine
translation. We introduce latency BLEU
(LBLEU), which takes into
account the expeditiousness of the simultaneous
translation system.
LBLEU sums the BLEU scores of the
incremental translations, while
weighting the final translation in proportion to the
sentence size.
As a result, translations that are fast and accurate, as
opposed to merely fast or accurate, achieve higher scores.
[PDF]
[Video]
[BibTeX]