Related papers: Accelerating NMT Batched Beam Decoding with LMBR P…
Despite the remarkable strides made by autoregressive language models, their potential is often hampered by the slow inference speeds inherent in sequential token generation. Blockwise parallel decoding (BPD) was proposed by Stern et al. as…
Recent studies have shown that reinforcement learning (RL) is an effective approach for improving the performance of neural machine translation (NMT) system. However, due to its instability, successfully RL training is challenging,…
With the rapid development of artificial intelligence (AI), there is a trend in moving AI applications, such as neural machine translation (NMT), from cloud to mobile devices. Constrained by limited hardware resources and battery, the…
Neural machine translation (NMT) becomes a new approach to machine translation and generates much more fluent results compared to statistical machine translation (SMT). However, SMT is usually better than NMT in translation adequacy. It is…
Memory and computation efficient deep learning architec- tures are crucial to continued proliferation of machine learning capabili- ties to new platforms and systems. Binarization of operations in convo- lutional neural networks has shown…
Despite the impressive performance of LLMs, their widespread adoption faces challenges due to substantial computational and memory requirements during inference. Recent advancements in model compression and system-level optimization methods…
In neural machine translation (NMT), the most common practice is to stack a number of recurrent or feed-forward layers in the encoder and the decoder. As a result, the addition of each new layer improves the translation quality…
In this paper we propose the Ray-Patch querying, a novel model to efficiently query transformers to decode implicit representations into target views. Our Ray-Patch decoding reduces the computational footprint and increases inference speed…
Recently, neural machine translation has achieved remarkable progress by introducing well-designed deep neural networks into its encoder-decoder framework. From the optimization perspective, residual connections are adopted to improve…
Stacking non-linear layers allows deep neural networks to model complicated functions, and including residual connections in Transformer layers is beneficial for convergence and performance. However, residual connections may make the model…
Multimodal Machine Translation (MMT) aims to improve translation quality by leveraging auxiliary modalities such as images alongside textual input. While recent advances in large-scale pre-trained language and vision models have…
Despite the progress in machine translation quality estimation and evaluation in the last years, decoding in neural machine translation (NMT) is mostly oblivious to this and centers around finding the most probable translation according to…
Recent studies have revealed a number of pathologies of neural machine translation (NMT) systems. Hypotheses explaining these mostly suggest there is something fundamentally wrong with NMT as a model or its training algorithm, maximum…
We propose a new class of information-coupled (IC) Turbo codes to improve the transport block (TB) error rate performance for long-term evolution (LTE) systems, while keeping the hybrid automatic repeat request protocol and the Turbo…
Belief Propagation (BP) decoding of LDPC codes is extended to the case of Joint Source-Channel coding. The uncompressed source is treated as a Markov process, characterized by a transition matrix, T, which is utilized as side information…
Decoding methods play an indispensable role in converting language models from next-token predictors into practical task solvers. Prior research on decoding methods, primarily focusing on task-specific models, may not extend to the current…
Recent advances in machine translation (MT) have shown that Minimum Bayes Risk (MBR) decoding can be a powerful alternative to beam search decoding, especially when combined with neural-based utility functions. However, the performance of…
Advanced neural machine translation (NMT) models generally implement encoder and decoder as multiple layers, which allows systems to model complex functions and capture complicated linguistic structures. However, only the top layers of…
As neural machine translation (NMT) is not easily amenable to explicit correction of errors, incorporating pre-specified translations into NMT is widely regarded as a non-trivial challenge. In this paper, we propose and explore three…
We introduce the Normalized Matching Transformer (NMT), a deep learning approach for efficient and accurate sparse semantic keypoint matching between image pairs. NMT consists of a strong visual backbone, geometric feature refinement via…