Language Model Augmented Monotonic Attention for Simultaneous Translation
The state-of-the-art adaptive policies for Simultaneous Neural Machine Translation (SNMT) use monotonic attention to perform read/write decisions based on the partial source and target sequences. The lack of sufficient information might cause the monotonic attention to take poor read/write decisions, which in turn negatively affects the performance of the SNMT model. On the other hand, human translators make better read/write decisions since they can anticipate the immediate future words using linguistic information and domain knowledge. In this work, we propose a framework to aid monotonic attention with an external language model to improve its decisions. Experiments on MuST-C English-German and English-French speech-to-text translation tasks show the future information from the language model improves the state-of-the-art monotonic multi-head attention model further.
Code (0)
등록된 구현이 없습니다.
Tasks
Language ModelingLanguage ModellingMachine TranslationmodelSpeech-to-TextSpeech-to-Text TranslationTranslationSimilar Papers 제목 키워드 기반
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+3Efficient Monotonic Multihead Attention
We introduce the Efficient Monotonic Multihead Attention (EMMA), a state-of-the-art simultaneous translation model with numerically-stable and unbiased monotonic alignment estimation. In addition, we present improved tra…
Simultaneous Speech-to-Text TranslationSpeech-to-TextSpeech-to-Text TranslationTranslationThe USTC-NELSLIP Systems for Simultaneous Speech Translation Task at IWSLT 2021
This paper describes USTC-NELSLIP's submissions to the IWSLT2021 Simultaneous Speech Translation task. We proposed a novel simultaneous translation model, Cross Attention Augmented Transducer (CAAT), which extends conven…
Data AugmentationSpeech-to-TextTranslationMonotonic Infinite Lookback Attention for Simultaneous Machine Translation
Simultaneous machine translation begins to translate each source sentence before the source speaker is finished speaking, with applications to live and streaming scenarios. Simultaneous systems must carefully schedule th…
Machine TranslationNMTSentenceTranslationInfusing Future Information into Monotonic Attention Through Language Models
Simultaneous neural machine translation(SNMT) models start emitting the target sequence before they have processed the source sequence. The recent adaptive policies for SNMT use monotonic attention to perform read/write …
Language ModelingLanguage ModellingMachine TranslationSpeech-to-Text+2