Modeling Dual Read/Write Paths for Simultaneous Machine Translation
Simultaneous machine translation (SiMT) outputs translation while reading source sentence and hence requires a policy to decide whether to wait for the next source word (READ) or generate a target word (WRITE), the actions of which form a read/write path. Although the read/write path is essential to SiMT performance, no direct supervision is given to the path in the existing methods. In this paper, we propose a method of dual-path SiMT which introduces duality constraints to direct the read/write path. According to duality constraints, the read/write path in source-to-target and target-to-source SiMT models can be mapped to each other. As a result, the two SiMT models can be optimized jointly by forcing their read/write paths to satisfy the mapping. Experiments on En-Vi and De-En tasks show that our method can outperform strong baselines under all latency.
Code (1)
Tasks
de-enMachine TranslationSentenceTranslationSimilar Papers 제목 키워드 기반
Self-Modifying State Modeling for Simultaneous Machine Translation
Simultaneous Machine Translation (SiMT) generates target outputs while receiving stream source inputs and requires a read/write policy to decide whether to wait for the next source token or generate a new target token, w…
Machine TranslationTranslationEyettention: An Attention-based Dual-Sequence Model for Predicting Human Scanpaths during Reading
Eye movements during reading offer insights into both the reader's cognitive processes and the characteristics of the text that is being read. Hence, the analysis of scanpaths in reading have attracted increasing attenti…
Cross Attention Augmented Transducer Networks for Simultaneous Translation
This paper proposes a novel architecture, Cross Attention Augmented Transducer (CAAT), for simultaneous translation. The framework aims to jointly optimize the policy and translation models. To effectively consider all p…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Decoderspeech-recognition+3Residual Networks Behave Like Ensembles of Relatively Shallow Networks
In this work we propose a novel interpretation of residual networks showing that they can be seen as a collection of many paths of differing length. Moreover, residual networks seem to enable very deep networks by levera…
Non-Monotonic Attention-based Read/Write Policy Learning for Simultaneous Translation
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 mode…
Binary ClassificationMachine TranslationTranslation