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 full-sentence translation, we propose a novel prefix-to-prefix framework for simultaneous translation that implicitly learns to anticipate in a single translation model. Within this framework, we present a very simple yet surprisingly effective "wait-k" policy trained to generate the target sentence concurrently with the source sentence, but always k words behind. Experiments show our strategy achieves low latency and reasonable quality (compared to full-sentence translation) on 4 directions: zh↔en and de↔en. * M.M. and L.H. contributed equally; L.H. conceived the main ideas (prefix-to-prefix and wait-k) and directed the project, while M.M. led the implementations on RNN and Transformer. See example videos, media reports, code, and data at https://simultrans-demo.github.io/. President Bush met with Putin in MoscowBùshí Bush zǒngtǒng President zài at Mòsīkē Moscow yǔ with Pǔjīng Putin huìwù meet prediction read write Source side → Target side → 2 Preliminaries: Full-Sentence NMT We first briefly review standard (full-sentence) neural translation to set up the notations.Regardless of the particular design of different seq-to-seq models, the encoder always takes
Obstructive sleep apnea (OSA) syndrome is a common sleep disorder suffered by an increasing number of people worldwide. As an alternative to polysomnography (PSG) for OSA diagnosis, the automatic OSA detection methods used in the current practice mainly concentrate on feature extraction and classifier selection based on collected physiological signals. However, one common limitation in these methods is that the temporal dependence of signals are usually ignored, which may result in critical information loss for OSA diagnosis. In this study, we propose a novel OSA detection approach based on ECG signals by considering temporal dependence within segmented signals. A discriminative hidden Markov model (HMM) and corresponding parameter estimation algorithms are provided. In addition, subject-specific transition probabilities within the model are employed to characterize the subject-to-subject differences of potential OSA patients. To validate our approach, 70 recordings obtained from the Physionet Apnea-ECG database were used. Accuracies of 97.1% for per-recording classification and 86.2% for per-segment OSA detection with satisfactory sensitivity and specificity were achieved. Compared with other existing methods that simply ignore the temporal dependence of signals, the proposed HMM-based detection approach delivers more satisfactory detection performance and could be extended to other disease diagnosis applications.
Motivation Predicting the secondary structure of an ribonucleic acid (RNA) sequence is useful in many applications. Existing algorithms [based on dynamic programming] suffer from a major limitation: their runtimes scale cubically with the RNA length, and this slowness limits their use in genome-wide applications. Results We present a novel alternative O(n3)-time dynamic programming algorithm for RNA folding that is amenable to heuristics that make it run in O(n) time and O(n) space, while producing a high-quality approximation to the optimal solution. Inspired by incremental parsing for context-free grammars in computational linguistics, our alternative dynamic programming algorithm scans the sequence in a left-to-right (5′-to-3′) direction rather than in a bottom-up fashion, which allows us to employ the effective beam pruning heuristic. Our work, though inexact, is the first RNA folding algorithm to achieve linear runtime (and linear space) without imposing constraints on the output structure. Surprisingly, our approximate search results in even higher overall accuracy on a diverse database of sequences with known structures. More interestingly, it leads to significantly more accurate predictions on the longest sequence families in that database (16S and 23S Ribosomal RNAs), as well as improved accuracies for long-range base pairs (500+ nucleotides apart), both of which are well known to be challenging for the current models. Availability and implementation Our source code is available at https://github.com/LinearFold/LinearFold, and our webserver is at http://linearfold.org (sequence limit: 100 000nt). Supplementary information Supplementary data are available at Bioinformatics online.
BackgroundPrevious studies have reported decreased birth weight associated with increased air pollutant concentrations during pregnancy. However, it is not clear when during pregnancy increases in air pollution are associated with the largest differences in birth weight.ObjectivesUsing the natural experiment of air pollution declines during the 2008 Beijing Olympics, we evaluated whether having specific months of pregnancy (i.e., 1st…8th) during the 2008 Olympics period was associated with larger birth weights, compared with pregnancies during the same dates in 2007 or 2009.MethodsUsing n = 83,672 term births to mothers residing in four urban districts of Beijing, we estimated the difference in birth weight associated with having individual months of pregnancy during the 2008 Olympics (8 August–24 September 2008) compared with the same dates in 2007 and 2009. We also estimated the difference in birth weight associated with interquartile range (IQR) increases in mean ambient particulate matter ≤ 2.5 μm in aerodynamic diameter (PM2.5), sulfur dioxide (SO2), nitrogen dioxide (NO2), and carbon monoxide (CO) concentrations during each pregnancy month.ResultsBabies whose 8th month of gestation occurred during the 2008 Olympics were, on average, 23 g larger (95% CI: 5 g, 40 g) than babies whose 8th month occurred during the same calendar dates in 2007 or 2009. IQR increases in PM2.5 (19.8 μg/m3), CO (0.3 ppm), SO2 (1.8 ppb), and NO2 (13.6 ppb) concentrations during the 8th month of pregnancy were associated with 18 g (95% CI: –32 g, –3 g), 17 g (95% CI: –28 g, –6 g), 23 g (95% CI: –36 g, –10 g), and 34 g (95% CI: –70 g, 3 g) decreases in birth weight, respectively. We did not see significant associations for months 1–7.ConclusionsShort-term decreases in air pollution late in pregnancy in Beijing during the 2008 Summer Olympics, a normally heavily polluted city, were associated with higher birth weight.CitationRich DQ, Liu K, Zhang J, Thurston SW, Stevens TP, Pan Y, Kane C, Weinberger B, Ohman-Strickland P, Woodruff TJ, Duan X, Assibey-Mensah V, Zhang J. 2015. Differences in birth weight associated with the 2008 Beijing Olympics air pollution reduction: results from a natural experiment. Environ Health Perspect 123:880–887; http://dx.doi.org/10.1289/ehp.1408795
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.