No abstract

Altered structural brain asymmetry in autism spectrum disorder (ASD) has been reported. However, findings have been inconsistent, likely due to limited sample sizes. Here we investigated 1,774 individuals with ASD and 1,809 controls, from 54 independent data sets of the ENIGMA consortium. ASD was significantly associated with alterations of cortical thickness asymmetry in mostly medial frontal, orbitofrontal, cingulate and inferior temporal areas, and also with asymmetry of orbitofrontal surface area. These differences generally involved reduced asymmetry in individuals with ASD compared to controls. Furthermore, putamen volume asymmetry was significantly increased in ASD. The largest case-control effect size was Cohen’s d = −0.13, for asymmetry of superior frontal cortical thickness. Most effects did not depend on age, sex, IQ, severity or medication use. Altered lateralized neurodevelopment may therefore be a feature of ASD, affecting widespread brain regions with diverse functions. Large-scale analysis was necessary to quantify subtle alterations of brain structural asymmetry in ASD.

Fully non-autoregressive neural machine translation (NAT) simultaneously predicts tokens with single forward of neural networks, which significantly reduces the inference latency at the expense of quality drop compared to the Transformer baseline. In this work, we target on closing the performance gap while maintaining the latency advantage. We first inspect the fundamental issues of fully NAT models, and adopt dependency reduction in the learning space of output tokens as the primary guidance. Then, we revisit methods in four different aspects that have been proven effective for improving NAT models, and carefully combine these techniques with necessary modifications. Our extensive experiments on three translation benchmarks show that the proposed system achieves the state-of-the-art results for fully NAT models, and obtains comparable performance with the autoregressive and iterative NAT systems. For instance, one of the proposed models achieves 27.49 BLEU points on WMT14 En-De with 16.5× speed-up compared to similar sized autoregressive baseline under the same inference condition. The implementation of our model is available here 1 .

Translation to or from low-resource languages (LRLs) poses challenges for machine translation in terms of both adequacy and fluency. Data augmentation utilizing large amounts of monolingual data is regarded as an effective way to alleviate these problems. In this paper, we propose a general framework for data augmentation in low-resource machine translation that not only uses target-side monolingual data, but also pivots through a related highresource language (HRL). Specifically, we experiment with a two-step pivoting method to convert high-resource data to the LRL, making use of available resources to better approximate the true data distribution of the LRL. First, we inject LRL words into HRL sentences through an induced bilingual dictionary. Second, we further edit these modified sentences using a modified unsupervised machine translation framework. Extensive experiments on four low-resource datasets show that under extreme low-resource settings, our data augmentation techniques improve translation quality by up to 1.5 to 8 BLEU points compared to supervised back-translation baselines.

Although Neural Machine Translation (NMT) models have advanced state-of-the-art performance in machine translation, they face problems like the inadequate translation. We attribute this to that the standard Maximum Likelihood Estimation (MLE) cannot judge the real translation quality due to its several limitations. In this work, we propose an adequacyoriented learning mechanism for NMT by casting translation as a stochastic policy in Reinforcement Learning (RL), where the reward is estimated by explicitly measuring translation adequacy. Benefiting from the sequence-level training of RL strategy and a more accurate reward designed specifically for translation, our model outperforms multiple strong baselines, including (1) standard and coverage-augmented attention models with MLE-based training, and (2) advanced reinforcement and adversarial training strategies with rewards based on both word-level BLEU and character-level CHRF3. Quantitative and qualitative analyses on different language pairs and NMT architectures demonstrate the effectiveness and universality of the proposed approach.