Related papers: Efficient Machine Translation with a BiLSTM-Attent…

Pre-trained language models (e.g., BERT (Devlin et al., 2018) and its variants) have achieved remarkable success in varieties of NLP tasks. However, these models usually consist of hundreds of millions of parameters which brings challenges…

Large language models (LLMs) have recently demonstrated promising performance in simultaneous machine translation (SimulMT). However, applying decoder-only LLMs to SimulMT introduces a positional mismatch, which leads to a dilemma between…

The prevalent approaches of Chinese word segmentation task almost rely on the Bi-LSTM neural network. However, the methods based the Bi-LSTM have some inherent drawbacks: hard to parallel computing, little efficient in applying the Dropout…

Neural machine translation (NMT) offers a novel alternative formulation of translation that is potentially simpler than statistical approaches. However to reach competitive performance, NMT models need to be exceedingly large. In this paper…

Transformer-based models have emerged as a leading architecture for natural language processing, natural language generation, and image generation tasks. A fundamental element of the transformer architecture is self-attention, which allows…

The advent of the attention mechanism in neural machine translation models has improved the performance of machine translation systems by enabling selective lookup into the source sentence. In this paper, the efficiencies of translation…

In this paper a doubly attentive transformer machine translation model (DATNMT) is presented in which a doubly-attentive transformer decoder normally joins spatial visual features obtained via pretrained convolutional neural networks,…

There have been emerging research interest and advances in speech-to-speech translation (S2ST), translating utterances from one language to another. This work proposes Multitask Speech Language Model (MSLM), which is a decoder-only speech…

Simultaneous Machine Translation (SiMT) requires high-quality translations under strict real-time constraints, which traditional encoder-decoder policies with only READ/WRITE actions cannot fully address. We extend the action space of SiMT…

In this work, we demonstrate that multilingual large-scale sequence-to-sequence (seq2seq) models, pre-trained on a mixture of denoising and Causal Language Modeling (CLM) tasks, are more efficient few-shot learners than decoder-only models…

To improve the performance of Neural Machine Translation~(NMT) for low-resource languages~(LRL), one effective strategy is to leverage parallel data from a related high-resource language~(HRL). However, multilingual data has been found more…

Recent advances in transformer-based Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks. However, their quadratic computational complexity concerning sequence length remains a significant bottleneck…

Neural machine translation (NMT) aims at solving machine translation (MT) problems using neural networks and has exhibited promising results in recent years. However, most of the existing NMT models are shallow and there is still a…

Conventional attention-based Neural Machine Translation (NMT) conducts dynamic alignment in generating the target sentence. By repeatedly reading the representation of source sentence, which keeps fixed after generated by the encoder…

Large Vision-Language Models (VLMs) have achieved remarkable success in multi-modal reasoning, but their inference time efficiency remains a significant challenge due to the memory overhead during decoding, especially when the query and…

Real-world simultaneous machine translation (SimulMT) systems face more challenges than just the quality-latency trade-off. They also need to address issues related to robustness with noisy input, processing long contexts, and flexibility…

The growth in the number of parameters of Large Language Models (LLMs) has led to a significant surge in computational requirements, making them challenging and costly to deploy. Speculative decoding (SD) leverages smaller models to…

Recently, the Transformer model that is based solely on attention mechanisms, has advanced the state-of-the-art on various machine translation tasks. However, recent studies reveal that the lack of recurrence hinders its further improvement…

As Large Language Models (LLMs) can now process extremely long contexts, efficient inference over these extended inputs has become increasingly important, especially for emerging applications like LLM agents that highly depend on this…

Simultaneous machine translation (SimulMT) presents a challenging trade-off between translation quality and latency. Recent studies have shown that LLMs can achieve good performance in SimulMT tasks. However, this often comes at the expense…