Neural machine translation: Challenges, progress and future
Abstract Machine translation (MT) is a technique that leverages computers to translate
human languages automatically. Nowadays, neural machine translation (NMT) which …
human languages automatically. Nowadays, neural machine translation (NMT) which …
STACL: Simultaneous translation with implicit anticipation and controllable latency using prefix-to-prefix framework
Simultaneous translation, which translates sentences before they are finished, is useful in
many scenarios but is notoriously difficult due to word-order differences. While the …
many scenarios but is notoriously difficult due to word-order differences. While the …
Monotonic multihead attention
Simultaneous machine translation models start generating a target sequence before they
have encoded or read the source sequence. Recent approaches for this task either apply a …
have encoded or read the source sequence. Recent approaches for this task either apply a …
SimulMT to SimulST: Adapting simultaneous text translation to end-to-end simultaneous speech translation
Simultaneous text translation and end-to-end speech translation have recently made great
progress but little work has combined these tasks together. We investigate how to adapt …
progress but little work has combined these tasks together. We investigate how to adapt …
Information-transport-based policy for simultaneous translation
Simultaneous translation (ST) outputs translation while receiving the source inputs, and
hence requires a policy to determine whether to translate a target token or wait for the next …
hence requires a policy to determine whether to translate a target token or wait for the next …
SimulSpeech: End-to-end simultaneous speech to text translation
In this work, we develop SimulSpeech, an end-to-end simultaneous speech to text
translation system which translates speech in source language to text in target language …
translation system which translates speech in source language to text in target language …
Simpler and faster learning of adaptive policies for simultaneous translation
Simultaneous translation is widely useful but remains challenging. Previous work falls into
two main categories:(a) fixed-latency policies such as Ma et al.(2019) and (b) adaptive …
two main categories:(a) fixed-latency policies such as Ma et al.(2019) and (b) adaptive …
SIMULEVAL: An evaluation toolkit for simultaneous translation
Simultaneous translation on both text and speech focuses on a real-time and low-latency
scenario where the model starts translating before reading the complete source input …
scenario where the model starts translating before reading the complete source input …
Efficient wait-k models for simultaneous machine translation
Simultaneous machine translation consists in starting output generation before the entire
input sequence is available. Wait-k decoders offer a simple but efficient approach for this …
input sequence is available. Wait-k decoders offer a simple but efficient approach for this …
Learning adaptive segmentation policy for simultaneous translation
Balancing accuracy and latency is a great challenge for simultaneous translation. To
achieve high accuracy, the model usually needs to wait for more streaming text before …
achieve high accuracy, the model usually needs to wait for more streaming text before …