Kavli Affiliate: Zeeshan Ahmed
| First 5 Authors: Zeeshan Ahmed, Frank Seide, Zhe Liu, Rastislav Rabatin, Jachym Kolar
| Summary:
Simultaneous or streaming machine translation generates translation while
reading the input stream. These systems face a quality/latency trade-off,
aiming to achieve high translation quality similar to non-streaming models with
minimal latency. We propose an approach that efficiently manages this
trade-off. By enhancing a pretrained non-streaming model, which was trained
with a seq2seq mechanism and represents the upper bound in quality, we convert
it into a streaming model by utilizing the alignment between source and target
tokens. This alignment is used to learn a read/write decision boundary for
reliable translation generation with minimal input. During training, the model
learns the decision boundary through a read/write policy module, employing
supervised learning on the alignment points (pseudo labels). The read/write
policy module, a small binary classification unit, can control the
quality/latency trade-off during inference. Experimental results show that our
model outperforms several strong baselines and narrows the gap with the
non-streaming baseline model.
| Search Query: ArXiv Query: search_query=au:”Zeeshan Ahmed”&id_list=&start=0&max_results=3