Related papers: Future-Guided Incremental Transformer for Simultan…
In simultaneous translation (SimulMT), the most widely used strategy is the wait-k policy thanks to its simplicity and effectiveness in balancing translation quality and latency. However, wait-k suffers from two major limitations: (a) it is…
Simultaneous machine translation aims at solving the task of real-time translation by starting to translate before consuming the full input, which poses challenges in terms of balancing quality and latency of the translation. The wait-$k$…
Simultaneous translation is widely useful but remains one of the most difficult tasks in NLP. Previous work either uses fixed-latency policies, or train a complicated two-staged model using reinforcement learning. We propose a much simpler…
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 problem. They first read k source tokens, after which they…
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 source token. The major challenge of ST is that each…
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 conventional seq-to-seq framework is only suitable for…
Simultaneous machine translation (SimulMT) speeds up the translation process by starting to translate before the source sentence is completely available. It is difficult due to limited context and word order difference between languages.…
This paper addresses the problem of simultaneous machine translation (SiMT) by exploring two main concepts: (a) adaptive policies to learn a good trade-off between high translation quality and low latency; and (b) visual information to…
Speech-to-text translation (ST), which translates source language speech into target language text, has attracted intensive attention in recent years. Compared to the traditional pipeline system, the end-to-end ST model has potential…
Simultaneous machine translation (SiMT) generates translation before reading the entire source sentence and hence it has to trade off between translation quality and latency. To fulfill the requirements of different translation quality and…
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 policies such as Gu et al. (2017). The former are simple…
We address the problem of simultaneous translation by modifying the Neural MT decoder to operate with dynamically built encoder and attention. We propose a tunable agent which decides the best segmentation strategy for a user-defined BLEU…
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 simultaneous text translation methods such as wait-k and…
Simultaneous machine translation (SiMT) generates translation while reading the whole source sentence. However, existing SiMT models are typically trained using the same reference disregarding the varying amounts of available source…
Speech translation (ST) aims to learn transformations from speech in the source language to the text in the target language. Previous works show that multitask learning improves the ST performance, in which the recognition decoder generates…
A popular approach to streaming speech translation is to employ a single offline model with a wait-k policy to support different latency requirements, which is simpler than training multiple online models with different latency constraints.…
The study of the attention mechanism has sparked interest in many fields, such as language modeling and machine translation. Although its patterns have been exploited to perform different tasks, from neural network understanding to textual…
Transformer models using segment-based processing have been an effective architecture for simultaneous speech translation. However, such models create a context mismatch between training and inference environments, hindering potential…
End-to-end simultaneous speech translation (SST), which directly translates speech in one language into text in another language in real-time, is useful in many scenarios but has not been fully investigated. In this work, we propose…
Simultaneous speech translation (SST) outputs translations in parallel with streaming speech input, balancing translation quality and latency. While large language models (LLMs) have been extended to handle the speech modality, streaming…