,
5 tweets,
2 min read
Read on Twitter
ACL keynote#1 Liang Huang: Simultaneous Translation (Machine Interpretation)
One of the main reasons for latency in Simultaneous Machine Translation is the problem of Word order (e.g. German verb comes at the end) #ACL2019nlp
One of the main reasons for latency in Simultaneous Machine Translation is the problem of Word order (e.g. German verb comes at the end) #ACL2019nlp
Current solutions in industry at the moment was to translate sentence by sentence which will introduce some latency. Work in academia include methods that either anticipates the "German verb" on the source-side.
or RL to keep waiting for the german verb (Gu et al. 2017)
or RL to keep waiting for the german verb (Gu et al. 2017)
"prefix to prefix translation" is to pull the effort of the anticipation of the late verb on the LM of the decoder with a wait K policy which is very natural to what interpreters do in real life.
One of the bi-products of their research is a new latency metric that resembles the "ear voice span" metric of interpretation.
@threadreaderapp unroll
