Related papers: Centroid-Based Efficient Minimum Bayes Risk Decodi…
This paper describes our submission to the WMT20 sentence filtering task. We combine scores from (1) a custom LASER built for each source language, (2) a classifier built to distinguish positive and negative pairs by semantic alignment, and…
Autoregressive decoding limits the efficiency of transformers for Machine Translation (MT). The community proposed specific network architectures and learning-based methods to solve this issue, which are expensive and require changes to the…
In cell-free massive multiple-input multiple-output (MIMO) the fluctuations of the channel gain from the access points to a user are large due to the distributed topology of the system. Because of these fluctuations, data decoding schemes…
This paper presents a new preprocessing method to correct blinking artifacts in Electroencephalography (EEG) based Brain-Computer Interfaces (BCIs). This Algorithm for Blink Correction (ABC) directly corrects the signal in the time domain…
Neural machine translation models rely on the beam search algorithm for decoding. In practice, we found that the quality of hypotheses in the search space is negatively affected owing to the fixed beam size. To mitigate this problem, we…
As chiplet-based integration advances, designers must select among short-reach die-to-die interconnect technologies with widely varying shoreline and areal bandwidth density, energy per bit, reach, and raw bit error rate (BER). Meeting…
We extend the traditional framework for estimating subspace bases that maximize the preserved signal energy to additionally preserve the Cram\'er-Rao bound (CRB) of the biophysical parameters and, ultimately, improve accuracy and precision…
Mendelian randomization (MR) is a widely used tool for causal inference in the presence of unmeasured confounders, which uses single nucleotide polymorphisms (SNPs) as instrumental variables to estimate causal effects. However, SNPs often…
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…
Reinforcement learning has shown great promise in aligning language models with human preferences in a variety of text generation tasks, including machine translation. For translation tasks, rewards can easily be obtained from quality…
Decompilation is the procedure of transforming binary programs into a high-level representation, such as source code, for human analysts to examine. While modern decompilers can reconstruct and recover much information that is discarded…
In this paper, we propose a low latency, robust and scalable neural net based decoder for convolutional and low-density parity-check (LPDC) coding schemes. The proposed decoders are demonstrated to have bit error rate (BER) and block error…
Firstly, a sequential symmetry adaptation procedure is derived for semidirect product groups. Then, this sequential symmetry adaptation procedure is used in the development of new method named Monomer Basis Representation (MBR) for…
This paper introduces an enhanced normalized min-sum decoder designed to address the performance and complexity challenges associated with developing parallelizable decoders for short BCH codes in high-throughput applications. The decoder…
We propose a method that substantially improves the efficiency of deep distance metric learning based on the optimization of the triplet loss function. One epoch of such training process based on a naive optimization of the triplet loss…
Blurring mean shift (BMS) algorithm, a variant of the mean shift algorithm, is a kernel-based iterative method for data clustering, where data points are clustered according to their convergent points via iterative blurring. In this paper,…
A novel method for fast and high-resolution metabolic imaging, called ECcentric Circle ENcoding TRajectorIes for Compressed sensing (ECCENTRIC), has been developed and implemented at 7 Tesla MRI. ECCENTRIC is a non-Cartesian…
In Neural Machine Translation (NMT), the decoder can capture the features of the entire prediction history with neural connections and representations. This means that partial hypotheses with different prefixes will be regarded differently…
Background and Objective: Processing electrophysiological signals often requires blind source separation (BSS) due to the nature of mixing source signals. However, its complex computational demands make real-time BSS challenging. The…
Critical Error Detection (CED) in machine translation aims to determine whether a translation is safe to use or contains unacceptable deviations in meaning. While the WMT21 English-German CED dataset provided the first benchmark, it is…