虽然我们注意临床自然语言处理(NLP)的最新进展,但我们可以注意到临床和翻译研究界的一些抵抗,因为透明度,可解释性和可用性有限,采用NLP模型。在这项研究中,我们提出了一种开放的自然语言处理开发框架。我们通过实施NLP算法为国家Covid队列协作(N3C)进行了评估。基于Covid-19相关临床笔记的信息提取的利益,我们的工作包括1)使用Covid-19标志和症状作为用例的开放数据注释过程,2)一个社区驱动的规则集合平台,3)合成文本数据生成工作流程,用于生成信息提取任务的文本而不涉及人为受试者。 Corpora来自来自三个不同机构的文本(Mayo Clinic,肯塔基州大学,明尼苏达大学)。用单个机构(Mayo)规则集进行了金标准注释。这导致了0.876,0.706和0.694的F-Scors分别用于Mayo,Minnesota和肯塔基测试数据集。作为N3C NLP子群体的联盟努力的研究表明,创建联邦NLP算法开发和基准测试平台的可行性,以增强多机构临床NLP研究和采用。虽然我们在这项工作中使用Covid-19作为用例,但我们的框架足以适用于临床NLP的其他兴趣领域。
translated by 谷歌翻译
Recent work has shown that fine-tuning large pre-trained language models on a collection of tasks described via instructions, a.k.a. instruction-tuning, improves their zero and few-shot generalization to unseen tasks. However, there is a limited understanding of the performance trade-offs of different decisions made during the instruction-tuning process. These decisions include the scale and diversity of the instruction-tuning benchmark, different task sampling strategies, fine-tuning with and without demonstrations, training using specialized datasets for reasoning and dialogue, and finally, the fine-tuning objectives themselves. In this paper, we characterize the effect of instruction-tuning decisions on downstream task performance when scaling both model and benchmark sizes. To this end, we create OPT-IML Bench: a large benchmark for Instruction Meta-Learning (IML) of 2000 NLP tasks consolidated into task categories from 8 existing benchmarks, and prepare an evaluation framework to measure three types of model generalizations: to tasks from fully held-out categories, to held-out tasks from seen categories, and to held-out instances from seen tasks. Through the lens of this framework, we first present insights about instruction-tuning decisions as applied to OPT-30B and further exploit these insights to train OPT-IML 30B and 175B, which are instruction-tuned versions of OPT. OPT-IML demonstrates all three generalization abilities at both scales on four different evaluation benchmarks with diverse tasks and input formats -- PromptSource, FLAN, Super-NaturalInstructions, and UnifiedSKG. Not only does it significantly outperform OPT on all benchmarks but is also highly competitive with existing models fine-tuned on each specific benchmark. We release OPT-IML at both scales, together with the OPT-IML Bench evaluation framework.
translated by 谷歌翻译
Scaling up language models has led to unprecedented performance gains, but little is understood about how the training dynamics change as models get larger. How do language models of different sizes learn during pre-training? Why do larger language models demonstrate more desirable behaviors? In this paper, we analyze the intermediate training checkpoints of differently sized OPT models (Zhang et al.,2022)--from 125M to 175B parameters--on next-token prediction, sequence-level generation, and downstream tasks. We find that 1) at a given perplexity and independent of model sizes, a similar subset of training tokens see the most significant reduction in loss, with the rest stagnating or showing double-descent behavior; 2) early in training, all models learn to reduce the perplexity of grammatical sequences that contain hallucinations, with small models halting at this suboptimal distribution and larger ones eventually learning to assign these sequences lower probabilities; 3) perplexity is a strong predictor of in-context learning performance on 74 multiple-choice tasks from BIG-Bench, and this holds independent of the model size. Together, these results show that perplexity is more predictive of model behaviors than model size or training computation.
translated by 谷歌翻译
Prompting large language models has enabled significant recent progress in multi-step reasoning over text. However, when applied to text generation from semi-structured data (e.g., graphs or tables), these methods typically suffer from low semantic coverage, hallucination, and logical inconsistency. We propose MURMUR, a neuro-symbolic modular approach to text generation from semi-structured data with multi-step reasoning. MURMUR is a best-first search method that generates reasoning paths using: (1) neural and symbolic modules with specific linguistic and logical skills, (2) a grammar whose production rules define valid compositions of modules, and (3) value functions that assess the quality of each reasoning step. We conduct experiments on two diverse data-to-text generation tasks like WebNLG and LogicNLG. These tasks differ in their data representations (graphs and tables) and span multiple linguistic and logical skills. MURMUR obtains significant improvements over recent few-shot baselines like direct prompting and chain-of-thought prompting, while also achieving comparable performance to fine-tuned GPT-2 on out-of-domain data. Moreover, human evaluation shows that MURMUR generates highly faithful and correct reasoning paths that lead to 26% more logically consistent summaries on LogicNLG, compared to direct prompting.
translated by 谷歌翻译
自然界中多元化的生态学在许多物种中具有各种形式的群体行为。蝴蝶物种是随机飞行的突出物种之一,有点有见地,并将其转化为人造隐喻将导致巨大的可能性。本文认为一种这种隐喻称为蝴蝶交配优化(BMO)。在BMO中,BFLE遵循巡逻的交配现象,并同时捕获了多模式函数的所有局部优势。为了模仿该算法,设计了一个移动机器人(BFlyBot),以满足BMO算法中BFLE的功能。此外,多Bflybot群的设计旨在像蝴蝶本质上的作用,并遵循该算法的规则。实时实验是在多动物领域的BMO算法上进行的,并将信号源视为光源。实验结果表明,BMO算法适用于检测多个信号源,其运动的变化显着,即静态和动态。在静态信号源的情况下,随着BFlybot的初始位置的不同,收敛性在时间和平稳性方面受到影响。而具有不同阶梯尺寸的实验会导致它们在机器人的执行时间和速度方面的变化。在这项工作中,在动态环境中进行了实验,在该环境中,信号源在操纵和非操作场景中的运动。 Bflybot群能够检测到单个和多信号源,在两个固定点之间在两个固定点之间进行线性移动,以圆形,向上和向下运动。评估BMO现象,各种正在进行的和前瞻性的作品,例如中海船舶检测,讨论了空中搜索应用和地震预测。
translated by 谷歌翻译
专家层(MOES)的混合物通过条件计算实现语言模型的高效缩放。本文提出了一个详细的实证研究,自回归鞋语言模型与广泛的设置中的密集模型相比:在域外语言建模,零和少量射击和全部微调。除了微调外,我们发现Moes基本上更加计算效率。在更适度的培训预算下,MOES可以使用$ \ SIM值4倍的计算,符合密集模型的性能。该差距在比例下变窄,但我们最大的MOE模型(1.1T参数)始终如一地优于计算等效的密集模型(6.7b参数)。总体而言,这种表现差距在任务和域中有很大差异,表明MOE和密集模型以不值得研究的方式概括不同的方式。我们使我们的代码和模型公开可用于研究使用。
translated by 谷歌翻译
GPT-3等大型自回归语言模型是几秒钟的学习者,可以在没有微调的情况下执行各种语言任务。虽然已知这些模型能够共同代表许多不同的语言,但他们的培训数据由英语主导,可能限制了它们的交叉概括。在这项工作中,我们在覆盖多种语言的平衡语料库上培训多语言自回归语言模型,并在广泛的任务中研究他们几乎没有零点的学习能力。我们最大的模型,具有75亿参数,在20多种代表语言中,在几种代表语言中,在几种代表性语言中,在几种代表性语言中,在多语言型号推理中表现出可比大小的GPT-3(在0次设置和0次拍摄设置中的绝对精度改善+ 7.4% 4-拍摄设置中的9.4%)和自然语言推理(每次拍摄和4次设置中的每一个+ 5.4%)。在Flores-101机器翻译基准测试中,我们的模型优于GPT-3在182个翻译方向上有32个培训例子,同时超过45个方向的官方监督基线。我们介绍了模型成功和失败的位置的详细分析,特别是它尤其显示在某些任务中实现交叉语境的内容学习,而仍然存在改善表面的鲁棒性和适应没有a的任务的余地自然冻结形式。最后,我们评估我们在仇恨语音检测中以五种语言的仇恨语音检测的模型,并发现它具有与可比大小的GPT-3模型类似的限制。
translated by 谷歌翻译
传统上,文本聚类方法包含在多文件摘要(MDS)中作为一种用于应对相当大的信息重复的手段。集群被利用以表明信息显着性并避免冗余。这些方法集中在聚类句子上,即使密切相关的句子也通常包含非对齐信息。在这项工作中,我们重新审视聚类方法,将命题分组为更精确的信息对齐。具体而言,我们的方法检测到突出的命题,将它们聚集到释义集群中,并通过融合其命题来为每个集群生成代表性句子。我们的摘要方法在自动胭脂评分和人类偏好中,通过了在DUC 2004和TAC 2011数据集中的先前最先进的MDS方法。
translated by 谷歌翻译
键形提取已在单文件设置中进行了广泛的研究,并具有大量的方法,数据集和应用程序。相反,尽管具有描述文档集的实用性及其在摘要中的用途,但很少研究多文档键形键盘提取。此外,对于多文件键孔提取,不存在先前的数据集,从而阻碍了任务的进度。多文本处理的最新进展使该任务成为追求的更具吸引力的挑战。为了刺激这种追求,我们在这里介绍了该任务的第一个数据集MK-DUC-01,它可以用作新的基准测试,并在我们的数据上测试多个键形提取基线。此外,我们还提供了对任务的简短但全面的文献回顾。
translated by 谷歌翻译