[1606.02012] Can neural machine translation do simultaneous translation?open searchopen navigation menucontact arXivsubscribe to arXiv mailings

We investigate the potential of attention-based neural machine translation in simultaneous translation. We introduce a novel decoding algorithm, called simultaneous greedy decoding, that allows an existing neural machine translation model to begin translating before a full source sentence is received. This approach is unique from previous works on simultaneous translation in that segmentation and translation are done jointly to maximize the translation quality and that translating each segment is strongly conditioned on all the previous segments. This paper presents a first step toward building a full simultaneous translation system based on neural machine translation.

1 mentions: @kchonyc
Date: 2020/11/20 21:51

Referring Tweets

@kchonyc [Cho & Esipova, 2016] from the tutorial was rejected from the same conference in 2016 (and i never re-submitted it to anywhere else). not bitter, but this was one of the most fun projects i’ve done so far, because it was really just out of blue (for me). t.co/PVw8dZG8ST

Related Entries

Read more [1912.05827] An Efficient Explorative Sampling Considering the Generative Boundaries of Deep Generat...
0 users, 1 mentions 2020/02/13 20:21
Read more Soft $k$-NN - HackMD
0 users, 1 mentions 2020/02/25 15:50
Read more Algorithms for Hyper-Parameter Optimization
0 users, 1 mentions 2020/04/16 18:52
Read more Neural Covidex
0 users, 1 mentions 2020/05/03 03:51
Read more 수학도가 인공지능 연구에 기여하는 방법 – 과학의 지평자산 1자산 1
0 users, 3 mentions 2020/11/03 02:22