Despite their widespread adoption, neural conversation models have yet to exhibit natural chat capabilities with humans. In this research, we examine user utterances as causes and generated responses as effects, recognizing that changes in a cause should produce a different effect. To further explore this concept, we have compiled and expanded upon a new dataset called CausalDialogue through crowd-sourcing. This dataset includes multiple cause-effect pairs within a directed acyclic graph (DAG) structure. Our analysis reveals that traditional loss functions can struggle to effectively incorporate the DAG structure, leading us to propose a causality-enhanced method called Exponential Maximum Average Treatment Effect (ExMATE) to enhance the impact of causality at the utterance level in training neural conversation models. To evaluate the effectiveness of this approach, we have built a comprehensive benchmark using the CausalDialogue dataset leveraging large-scale pre-trained language models, and have assessed the results through both human and automatic evaluation metrics for coherence, diversity, and agility. Our findings show that current techniques are still unable to effectively address conversational DAGs, and that the ExMATE method can improve the diversity and agility of conventional loss functions while maintaining coherence.
translated by 谷歌翻译
Is it possible to leverage large scale raw and raw parallel corpora to build a general learned metric? Existing learned metrics have gaps to human judgements, are model-dependent or are limited to the domains or tasks where human ratings are available. In this paper, we propose SEScore2, a model-based metric pretrained over million-scale synthetic dataset constructed by our novel retrieval augmented data synthesis pipeline. SEScore2 achieves high correlation to human judgements without any human rating supervisions. Importantly, our unsupervised SEScore2 can outperform supervised metrics, which are trained on the News human ratings, at the TED domain. We evaluate SEScore2 over four text generation tasks across three languages. SEScore2 outperforms all prior unsupervised evaluation metrics in machine translation, speech translation, data-to-text and dialogue generation, with average Kendall improvements 0.158. SEScore2 even outperforms SOTA supervised BLEURT at data-to-text, dialogue generation and overall correlation.
translated by 谷歌翻译
视觉导航要求代理商遵循自然语言说明以达到特定目标。可见的环境和看不见的环境之间的巨大差异使代理商概括良好的挑战。先前的研究提出了数据增强方法,以明确或隐式地减轻数据偏见并提供概括的改进。但是,他们试图记住增强的轨迹,并在测试时忽略在看不见的环境下的分布变化。在本文中,我们提出了一个看不见的差异,预期视力和语言导航(戴维斯),该差异通过鼓励测试时间的视觉一致性来概括为看不见的环境。具体来说,我们设计了:1)半监督框架戴维斯(Davis),该框架利用类似的语义观测来利用视觉一致性信号。 2)一个两阶段的学习程序,鼓励适应测试时间分布。该框架增强了模仿和强化学习的基本混合物与动量形成对比,以鼓励在联合训练阶段和测试时间适应阶段对类似观察的稳定决策。广泛的实验表明,戴维斯在R2R和RXR基准上实现了与先前最先进的VLN基线相比,取得了模型不合命源性的改进。我们的源代码和数据是补充材料。
translated by 谷歌翻译
语言规划旨在通过分解为更简单的低级步骤来实现复杂的高级目标。这种程序推理能力对于诸如家用机器人和虚拟助手等应用至关重要。尽管语言规划是日常生活中人类的基本技能,但对于缺乏现实世界中缺乏深层常识性知识的大型语言模型(LLM)来说,这仍然是一个挑战。以前的方法需要手动示例或带注释的程序才能从LLM中获取此类能力。相比之下,本文提出了神经符号的因果语言规划师(CLAP),该策划者通过注入常识的提示从LLM中引起了程序知识。 LLMS中的预训练知识本质上是一种未观察到的混杂因素,它在任务和行动计划之间引起虚假的相关性。通过结构性因果模型(SCM)的镜头,我们提出了一个有效的策略,以构建提示作为对SCM的因果干预。我们的策略使用图形采样技术和符号程序执行者,正式从常识知识基础上形成结构化因果提示。拍手在Wikihow和机器人上获得最新的表现,在反事实环境下,人类评估的相对提高了5.28%。这表明在语义和顺序的因果语言规划中拍手的优势。
translated by 谷歌翻译
专家员工的文字式传输技术有可能改善科学社区成员与公众之间的沟通。专家制作的高质量信息往往充满了困难的术语外国人,努力了解。这是医疗领域的一个特别值得注意的问题,其中Layman经常在线医学文本混淆。目前,两个瓶颈干扰了建立高质量医学专家外延式转移系统的目标:曾经专家和外行术语的缺点是普及的预押医学域语言模型,缺乏并行的Corpora培训转让任务本身。为了缓解第一个问题,我们提出了一种新颖的语言模型(LM)预测任务,知识基础同化,从自我监督学习期间将来自专家和外行式医学术语术语的边缘的预先训练数据综合为LM的LM。 。要缓解第二个问题,我们使用基于边缘的标准在医学专家 - Layman域中建立大规模并行语料库。我们的实验表明,基于变压器的模型,以知识库同化和其他良好的预先预订任务对我们的新并行语料库进行了微调,这导致专家外部转账基准的相当大,达到了我们人类评估的平均相对改善总体成功率(OSR),达106%。我们释放我们的代码和并行语料库以供未来的研究。
translated by 谷歌翻译
General deep learning-based methods for infrared and visible image fusion rely on the unsupervised mechanism for vital information retention by utilizing elaborately designed loss functions. However, the unsupervised mechanism depends on a well designed loss function, which cannot guarantee that all vital information of source images is sufficiently extracted. In this work, we propose a novel interactive feature embedding in self-supervised learning framework for infrared and visible image fusion, attempting to overcome the issue of vital information degradation. With the help of self-supervised learning framework, hierarchical representations of source images can be efficiently extracted. In particular, interactive feature embedding models are tactfully designed to build a bridge between the self-supervised learning and infrared and visible image fusion learning, achieving vital information retention. Qualitative and quantitative evaluations exhibit that the proposed method performs favorably against state-of-the-art methods.
translated by 谷歌翻译
The formalization of existing mathematical proofs is a notoriously difficult process. Despite decades of research on automation and proof assistants, writing formal proofs remains arduous and only accessible to a few experts. While previous studies to automate formalization focused on powerful search algorithms, no attempts were made to take advantage of available informal proofs. In this work, we introduce Draft, Sketch, and Prove (DSP), a method that maps informal proofs to formal proof sketches, and uses the sketches to guide an automated prover by directing its search to easier sub-problems. We investigate two relevant setups where informal proofs are either written by humans or generated by a language model. Our experiments and ablation studies show that large language models are able to produce well-structured formal sketches that follow the same reasoning steps as the informal proofs. Guiding an automated prover with these sketches enhances its performance from 20.9% to 39.3% on a collection of mathematical competition problems.
translated by 谷歌翻译
语言模型(LMS)被证明具有对物理世界的常识知识,这对于在日常情况下完成任务至关重要。但是,LMS是否有能力为具体任务生成扎根的可执行计划,这仍然是一个悬而未决的问题。这是非常具有挑战性的,因为LMS没有“眼睛”或“手”来感知现实的环境。在这项工作中,我们展示了有关这个重要研究问题的第一个研究。我们首先提出了一个名为G-Planet的新型问题公式,它将其作为输入一个高级目标和在特定环境中的对象表。预期输出是一个计划,该计划包括逐步指令供代理执行。为了实现此问题的研究,我们建立了一个评估协议,并设计了一个专门的指标来评估计划的质量。在我们的广泛实验中,我们表明,为编码环境添加扁平表并使用迭代解码策略都可以提高LMS的基础计划能力。我们对结果的分析也导致有趣的非平凡发现。
translated by 谷歌翻译
我们在分布式设置中研究了可靠的主成分分析(RPCA)问题。RPCA的目的是在数据矩阵遭受稀疏错误的损坏时,找到原始数据矩阵的基本低排名估计。先前的研究开发了RPCA算法,这些算法可提供快速收敛的稳定溶液。但是,由于使用SVD或大型矩阵乘法,这些算法通常很难扩展,因此无法分布分布。在本文中,我们提出了基于共识分解的第一个分布式强大的主分析算法,称为DCF-PCA。我们证明了DCF-PCA的收敛性并在各种问题设置上评估DCF-PCA
translated by 谷歌翻译
联合学习(FL)提供了一个有效的范式,可以通过隐私保护训练机器学习模型。但是,最近的研究表明,由于可能是恶意和异质的当地代理商,FL受到各种安全,隐私和公平威胁的约束。例如,它容易受到仅贡献低质量数据的本地对抗药物的攻击,目的是损害具有高质量数据的人的性能。因此,这种攻击破坏了FL中公平性的现有定义,主要集中于某种绩效奇偶校验的概念。在这项工作中,我们旨在解决此限制,并通过对FL(FAA)的代理意识(FAA)提出正式的公平定义,该定义将当地代理的异质数据贡献考虑在内。此外,我们提出了基于代理聚类(焦点)的公平FL培训算法以实现FAA。从理论上讲,我们证明了线性模型的温和条件下的聚焦和最优性,并且具有有界平滑度的一般凸丢失函数。我们还证明,在线性模型和一般凸损耗函数下,与标准的FedAvg协议相比,FAA始终达到FAA衡量的更高公平性。从经验上讲,我们评估对四个数据集的重点,包括不同设置下的合成数据,图像和文本,并且我们表明,与FedAvg相比,基于FAA的焦点基于FAA的公平性显着更高,同时保持相似甚至更高的预测准确性。
translated by 谷歌翻译