Pre-trained models have achieved remarkable success in natural language processing (NLP). However, existing pre-training methods underutilize the benefits of language understanding for generation. Inspired by the idea of Generative Adversarial Networks (GANs), we propose a GAN-style model for encoder-decoder pre-training by introducing an auxiliary discriminator, unifying the ability of language understanding and generation in a single model. Our model, named as GanLM, is trained with two pre-training objectives: replaced token detection and replaced token denoising. Specifically, given masked source sentences, the generator outputs the target distribution and the discriminator predicts whether the target sampled tokens from distribution are incorrect. The target sentence is replaced with misclassified tokens to construct noisy previous context, which is used to generate the gold sentence. In general, both tasks improve the ability of language understanding and generation by selectively using the denoising data. Extensive experiments in language generation benchmarks show that GanLM with the powerful language understanding capability outperforms various strong pre-trained language models (PLMs) and achieves state-of-the-art performance.
translated by 谷歌翻译
This paper presents ReasonFormer, a unified reasoning framework for mirroring the modular and compositional reasoning process of humans in complex decision-making. Inspired by dual-process theory in cognitive science, the representation module (automatic thinking) and reasoning modules (controlled thinking) are decoupled to capture different levels of cognition. Upon the top of the representation module, the pre-trained reasoning modules are modular and professional in specific and fundamental reasoning skills (e.g., logic, simple QA, etc). To mimic the controlled compositional thinking process, different reasoning modules are dynamically activated and composed in both parallel and cascaded manners to control what reasoning skills are activated and how deep the reasoning process will be reached to solve the current problems. The unified reasoning framework solves multiple tasks with a single model, and is trained and inferred in an end-to-end manner. Evaluated on 11 datasets requiring different reasoning skills and complexity, ReasonFormer demonstrates substantial performance boosts, revealing the compositional reasoning ability. Few-shot experiments exhibit better generalization ability by learning to compose pre-trained skills for new tasks with limited data, and decoupling the representation module and the reasoning modules. Further analysis shows the modularity of reasoning modules as different tasks activate distinct reasoning skills at different reasoning depths.
translated by 谷歌翻译
任务概括是自然语言处理(NLP)的漫长挑战。最近的研究试图通过将NLP任务映射到人类可读的提示形式中来提高预训练语言模型的任务概括能力。但是,这些方法需要费力且不灵活的提示,并且在同一下游任务上的不同提示可能会获得不稳定的性能。我们提出了统一的架构提示,这是一种灵活且可扩展的提示方法,该方法会根据任务输入架构自动自动自定义每个任务的可学习提示。它在任务之间建模共享知识,同时保持不同任务架构的特征,从而增强任务概括能力。架构提示采用每个任务的明确数据结构,以制定提示,因此涉及几乎没有人类的努力。为了测试模式提示的任务概括能力,我们对各种一般NLP任务进行基于模式提示的多任务预训练。该框架在从8种任务类型(例如QA,NLI等)的16个看不见的下游任务上实现了强劲的零射击和很少的概括性能。此外,全面的分析证明了每个组件在架构提示中的有效性,其在任务组成性方面的灵活性以及在全DATA微调设置下提高性能的能力。
translated by 谷歌翻译
变压器结构由一系列编码器和解码器网络层堆叠,在神经机器翻译中实现了重大发展。但是,假设下层提供了微不足道或冗余的信息,那么香草变压器主要利用顶层表示形式,从而忽略了潜在有价值的底层特征。在这项工作中,我们提出了组转换器模型(GTRAN),该模型将编码器和解码器的多层表示分为不同的组,然后融合这些组特征以生成目标词。为了证实所提出方法的有效性,对三个双语翻译基准和两个多语言翻译任务进行了广泛的实验和分析实验,包括IWLST-14,IWLST-17,IWLST-17,LDC,WMT-14和OPUS-100基准。实验和分析结果表明,我们的模型通过一致的增益优于其变压器对应物。此外,它可以成功扩展到60个编码层和36个解码器层。
translated by 谷歌翻译
通过多种语言对培训的多语言神经机器翻译(MNMT),由于模型参数的较少和较低的培训成本,通过在多种语言之间共享知识,引起了人们的关注。尽管如此,由于不同翻译方向之间的负面干扰,尤其是在高资源语言上,因此,多语言培训在共享参数中受到语言干扰退化的困扰。在本文中,我们提出了具有高资源语言特定培训(HLT-MT)的多语言翻译模型,以减轻负面干扰,该干扰采用了具有特定于语言的选择机制的两阶段培训。具体而言,我们首先仅使用高资源对训练多语言模型,然后选择解码器顶部的语言特定模块,以增强高资源方向的翻译质量。接下来,对所有可用语料库进行进一步培训,将知识从高资源语言(HRLS)转移到低资源语言(LRLS)。实验结果表明,HLT-MT在WMT-10和Opus-100基准测试上的表现优于各种强基础。此外,分析实验验证了我们方法在减轻多语言训练中负面干扰方面的有效性。
translated by 谷歌翻译
语言之间的大多数翻译任务都属于无法使用的零资源翻译问题。与两种通用枢轴翻译相比,多语言神经机器翻译(MNMT)可以使用所有语言的共享语义空间进行一通翻译,但通常表现不佳的基于枢轴的方法。在本文中,我们提出了一种新颖的方法,称为NMT(UM4)的统一多语言多语言多种教师模型。我们的方法统一了来源教师,目标老师和枢轴教师模型,以指导零资源翻译的学生模型。来源老师和目标教师迫使学生学习直接来源,以通过源头和目标方面的蒸馏知识进行目标翻译。枢轴教师模型进一步利用单语语料库来增强学生模型。实验结果表明,我们的72个方向模型在WMT基准测试上明显优于先前的方法。
translated by 谷歌翻译
私人随机梯度下降(DP-SGD)是私人深度学习最新进展的主力算法。它为数据集中的所有数据点提供了单个隐私保证。我们提出了一种有效的算法,以在释放由DP-SGD培训的模型时计算单个示例的隐私保证。我们使用算法来研究许多数据集中的个人隐私参数。我们发现,大多数示例比最严重的案例拥有更强的隐私保证。我们进一步发现,训练损失和示例的隐私参数是非常相关的。这意味着在模型效用方面服务不足的群体在隐私保证方面同时服务不足。例如,在CIFAR-10上,测试准确性最低的课程的平均$ \ epsilon $比班级的平均$ \ epsilon $高26.3%。我们还运行会员推理攻击,以表明这反映了不同的经验隐私风险。
translated by 谷歌翻译
Question Answering (QA) is a longstanding challenge in natural language processing. Existing QA works mostly focus on specific question types, knowledge domains, or reasoning skills. The specialty in QA research hinders systems from modeling commonalities between tasks and generalization for wider applications. To address this issue, we present ProQA, a unified QA paradigm that solves various tasks through a single model. ProQA takes a unified structural prompt as the bridge and improves the QA-centric ability by structural prompt-based pre-training. Through a structurally designed prompt-based input schema, ProQA concurrently models the knowledge generalization for all QA tasks while keeping the knowledge customization for every specific QA task. Furthermore, ProQA is pre-trained with structural prompt-formatted large-scale synthesized corpus, which empowers the model with the commonly-required QA ability. Experimental results on 11 QA benchmarks demonstrate that ProQA consistently boosts performance on both full data fine-tuning, few-shot learning, and zero-shot testing scenarios. Furthermore, ProQA exhibits strong ability in both continual learning and transfer learning by taking the advantages of the structural prompt.
translated by 谷歌翻译
许多真实世界图(网络)是具有不同类型的节点和边缘的异构。异构图嵌入,旨在学习异构图的低维节点表示,对于各种下游应用至关重要。已经提出了许多基于元路径的嵌入方法来学习近年来异构图的语义信息。然而,在学习异构图形嵌入时,大多数现有技术都在图形结构信息中忽略了图形结构信息。本文提出了一种新颖的结构意识异构图形神经网络(SHGNN),以解决上述限制。详细地,我们首先利用特征传播模块来捕获元路径中中间节点的本地结构信息。接下来,我们使用树关注聚合器将图形结构信息结合到元路径上的聚合模块中。最后,我们利用了元路径聚合器熔断来自不同元路径的聚合的信息。我们对节点分类和聚类任务进行了实验,并在基准数据集中实现了最先进的结果,该数据集显示了我们所提出的方法的有效性。
translated by 谷歌翻译
学习知识图的嵌入对人工智能至关重要,可以使各种下游应用受益,例如推荐和问题回答。近年来,已经提出了许多研究努力,以嵌入知识图形。然而,最先前的知识图形嵌入方法忽略不同三元组中的相关实体和实体关系耦合之间的语义相似性,因为它们与评分函数分别优化每个三倍。为了解决这个问题,我们提出了一个简单但有效的对比学习框架,用于知识图形嵌入,可以缩短不同三元组中相关实体和实体关系耦合的语义距离,从而提高知识图形嵌入的表现力。我们在三个标准知识图形基准上评估我们提出的方法。值得注意的是,我们的方法可以产生一些新的最先进的结果,在WN18RR数据集中实现51.2%的MRR,46.8%HITS @ 1,59.1%的MRR,51.8%在YAGO3-10数据集中击打@ 1 。
translated by 谷歌翻译