巨大的努力已经致力于创造高性能的少量学习者,即表现良好的培训数据的模型。培训大规模预训练语言模型(PLMS)产生了重大成本,但利用基于PLM的少量学习者由于其巨大尺寸而仍然具有挑战性。这项工作侧重于一个至关重要的问题:如何有效地利用这几个射门学习者?我们提出LMTurk,这是一种像众包工人一样对待几次射门学习者的新方法。理由是,众群工人实际上是几次学习者:他们被示出了一些说明性的例子来了解任务,然后开始注释。LMTurk聘请了几枪就是在PLMS作为工人的学习者。我们表明,由此产生的注释可以用来培训解决任务的模型,并且足够小,可以在实际情况下部署。完全,LMTurk是朝着有效利用当前PLM的少量学习者的重要一步。
translated by 谷歌翻译
我们提出了Patron,这是一种新方法,它使用基于及时的不确定性估计,用于在冷启动场景下进行预训练的语言模型进行微调的数据选择,即,没有初始标记的数据可用。在顾客中,我们设计(1)一种基于迅速的不确定性传播方法来估计数据点的重要性和(2)分区 - 然后 - 剥离(PTR)策略,以促进对注释的样品多样性。六个文本分类数据集的实验表明,赞助人的表现优于最强的冷启动数据选择基准,高达6.9%。此外,仅具有128个标签,顾客分别基于香草微调和及时的学习,获得了91.0%和92.1%的全面监督性能。我们的赞助人实施可在\ url {https://github.com/yueyu1030/patron}上获得。
translated by 谷歌翻译
积极的学习有效地收集了无标记的数据以进行注释,从而减少了对标记数据的需求。在这项工作中,我们建议以局部灵敏度和硬度感知的获取功能检索未标记的样品。所提出的方法通过局部扰动生成数据副本,并选择其预测可能性与其副本最大的数据点。我们通过注入选择的情况扰动来进一步增强我们的采集功能。我们的方法可以在各种分类任务中对常用的活跃学习策略获得一致的收益。此外,我们在基于迅速的几次学习中迅速选择的研究中观察到对基准的持续改进。这些实验表明,我们以局部敏感性和硬度为指导的获取对许多NLP任务都是有效和有益的。
translated by 谷歌翻译
尽管与专家标签相比,众包平台通常用于收集用于培训机器学习模型的数据集,尽管标签不正确。有两种常见的策略来管理这种噪音的影响。第一个涉及汇总冗余注释,但以较少的例子为代价。其次,先前的作品还考虑使用整个注释预算来标记尽可能多的示例,然后应用Denoising算法来隐式清洁数据集。我们找到了一个中间立场,并提出了一种方法,该方法保留了一小部分注释,以明确清理高度可能的错误样本以优化注释过程。特别是,我们分配了标签预算的很大一部分,以形成用于训练模型的初始数据集。然后,该模型用于确定最有可能是不正确的特定示例,我们将剩余预算用于重新标记。在三个模型变化和四个自然语言处理任务上进行的实验表明,当分配相同的有限注释预算时,旨在处理嘈杂标签的标签聚合和高级denoising方法均优于标签聚合或匹配。
translated by 谷歌翻译
How can we extend a pre-trained model to many language understanding tasks, without labeled or additional unlabeled data? Pre-trained language models (PLMs) have been effective for a wide range of NLP tasks. However, existing approaches either require fine-tuning on downstream labeled datasets or manually constructing proper prompts. In this paper, we propose nonparametric prompting PLM (NPPrompt) for fully zero-shot language understanding. Unlike previous methods, NPPrompt uses only pre-trained language models and does not require any labeled data or additional raw corpus for further fine-tuning, nor does it rely on humans to construct a comprehensive set of prompt label words. We evaluate NPPrompt against previous major few-shot and zero-shot learning methods on diverse NLP tasks: including text classification, text entailment, similar text retrieval, and paraphrasing. Experimental results demonstrate that our NPPrompt outperforms the previous best fully zero-shot method by big margins, with absolute gains of 12.8% in accuracy on text classification and 18.9% on the GLUE benchmark.
translated by 谷歌翻译
尽管在许多自然语言处理(NLP)任务中进行了预先训练的语言模型(LMS),但它们需要过多标记的数据来进行微调以实现令人满意的性能。为了提高标签效率,研究人员采取了活跃的学习(AL),而大多数事先工作则忽略未标记数据的潜力。要释放未标记数据的强大功能以获得更好的标签效率和模型性能,我们开发ATM,一个新的框架,它利用自我训练来利用未标记的数据,并且对于特定的AL算法不可知,用作改善现有的插件模块Al方法。具体地,具有高不确定性的未标记数据暴露于Oracle以进行注释,而具有低不确定性的人则可用于自培训。为了缓解自我训练中的标签噪声传播问题,我们设计一个简单且有效的基于动量的内存库,可以动态地从所有轮次汇总模型预测。通过广泛的实验,我们证明了ATM优于最强大的积极学习和自我训练基线,平均将标签效率提高51.9%。
translated by 谷歌翻译
由于表现强劲,预用的语言模型已成为许多NLP任务的标准方法,但他们培训价格昂贵。我们提出了一个简单高效的学习框架TLM,不依赖于大规模预制。给定一些标记的任务数据和大型常规语料库,TLM使用任务数据作为查询来检索一般语料库的微小子集,并联合优化任务目标和从头开始的语言建模目标。在四个域中的八个分类数据集上,TLM实现了比预用语言模型(例如Roberta-Light)更好地或类似的结果,同时减少了两个数量级的训练拖鞋。高精度和效率,我们希望TLM将有助于民主化NLP并加快发展。
translated by 谷歌翻译
Developed as a solution to a practical need, active learning (AL) methods aim to reduce label complexity and the annotations costs in supervised learning. While recent work has demonstrated the benefit of using AL in combination with large pre-trained language models (PLMs), it has often overlooked the practical challenges that hinder the feasibility of AL in realistic settings. We address these challenges by leveraging representation smoothness analysis to improve the effectiveness of AL. We develop an early stopping technique that does not require a validation set -- often unavailable in realistic AL settings -- and observe significant improvements across multiple datasets and AL methods. Additionally, we find that task adaptation improves AL, whereas standard short fine-tuning in AL does not provide improvements over random sampling. Our work establishes the usefulness of representation smoothness analysis in AL and presents an AL stopping criterion that reduces label complexity.
translated by 谷歌翻译
One of the most impressive results of recent NLP history is the ability of pre-trained language models to solve new tasks in a zero-shot setting. To achieve this, NLP tasks are framed as natural language prompts, generating a response indicating the predicted output. Nonetheless, the performance in such settings often lags far behind its supervised counterpart, suggesting a large space for potential improvement. In this paper, we explore methods to utilize unlabeled data to improve zero-shot performance. Specifically, we take advantage of the fact that multiple prompts can be used to specify a single task, and propose to regularize prompt consistency, encouraging consistent predictions over this diverse set of prompts. Our method makes it possible to fine-tune the model either with extra unlabeled training data, or directly on test input at inference time in an unsupervised manner. In experiments, our approach outperforms the state-of-the-art zero-shot learner, T0 (Sanh et al., 2022), on 9 out of 11 datasets across 4 NLP tasks by up to 10.6 absolute points in terms of accuracy. The gains are often attained with a small number of unlabeled examples.
translated by 谷歌翻译
Recent studies have revealed the intriguing few-shot learning ability of pretrained language models (PLMs): They can quickly adapt to a new task when fine-tuned on a small amount of labeled data formulated as prompts, without requiring abundant task-specific annotations. Despite their promising performance, most existing few-shot approaches that only learn from the small training set still underperform fully supervised training by nontrivial margins. In this work, we study few-shot learning with PLMs from a different perspective: We first tune an autoregressive PLM on the few-shot samples and then use it as a generator to synthesize a large amount of novel training samples which augment the original training set. To encourage the generator to produce label-discriminative samples, we train it via weighted maximum likelihood where the weight of each token is automatically adjusted based on a discriminative meta-learning objective. A classification PLM can then be fine-tuned on both the few-shot and the synthetic samples with regularization for better generalization and stability. Our approach FewGen achieves an overall better result across seven classification tasks of the GLUE benchmark than existing few-shot learning methods, improving no-augmentation methods by 5+ average points, and outperforming augmentation methods by 3+ average points.
translated by 谷歌翻译
With a handful of demonstration examples, large-scale language models show strong capability to perform various tasks by in-context learning from these examples, without any fine-tuning. We demonstrate that in-context learning performance can be highly unstable across samples of examples, indicating the idiosyncrasies of how language models acquire information. We formulate example selection for in-context learning as a sequential decision problem, and propose a reinforcement learning algorithm for identifying generalizable policies to select demonstration examples. For GPT-2, our learned policies demonstrate strong abilities of generalizing to unseen tasks in training, with a $5.8\%$ improvement on average. Examples selected from our learned policies can even achieve a small improvement on GPT-3 Ada. However, the improvement diminishes on larger GPT-3 models, suggesting emerging capabilities of large language models.
translated by 谷歌翻译
为了减轻数据稀缺性对事实检查系统的影响,我们专注于几乎没有声称验证。尽管最近通过提出高级语言模型进行了几次射击分类的工作,但数据注释优先级的研究缺乏研究,可以改善为最佳模型性能标记的少数镜头的选择。我们提出了活跃的宠物,这是一种新型的加权方法,它利用基于各种语言模型的模式开发培训(PET)模型的合奏来积极选择未标记的数据作为注释的候选者。使用活跃的宠物进行数据选择,在两个技术事实检查数据集上以及使用六个不同的预审前的语言模型上显示了对最先进的主动学习方法的一致改进。我们通过Active Pets-O展示了进一步的改进,该宠物O进一步整合了过采样策略。我们的方法使有效的实例可以被标记为无标记的数据丰富,但标签资源受到限制,从而始终改善了几次索赔验证性能。我们的代码将在出版后提供。
translated by 谷歌翻译
许多最新的自然语言任务方法都建立在大型语言模型的非凡能力上。大型语言模型可以执行内在的学习,他们可以从几个任务演示中学习新任务,而无需任何参数更新。这项工作研究了对新自然语言任务的数据集创建数据集的含义。与最近的文化学习方法背道而驰,我们制定了一个注释效率的两步框架:选择性注释,选择一个示例池,以提前从未标记的数据中从未标记的数据中进行注释,然后及时检索从注释的池中检索任务示例测试时间。基于此框架,我们提出了一种无监督的,基于图的选择性注释方法VOKE-K,以选择各种代表性的示例进行注释。在10个数据集上进行了广泛的实验(涵盖分类,常识性推理,对话和文本/代码生成)表明,我们的选择性注释方法通过很大的利润提高了任务性能。与随机选择示例进行注释相比,Pote-K平均在注释预算下获得了12.9%/11.4%的相对增益。与最先进的监督登录方法相比,它的性能相似,而在10个任务中的注释成本降低了10-100倍。我们在各种情况下进一步分析了框架的有效性:具有不同大小的语言模型,替代选择性注释方法以及有测试数据域移动的情况。我们希望我们的研究将作为数据注释的基础,因为大型语言模型越来越多地应用于新任务。我们的代码可在https://github.com/hkunlp/icl-selactive-annotation上找到。
translated by 谷歌翻译
最近的几种方法,例如参数有效的微调(PEFT)和模式开发训练(PET),在标签筛选设置中取得了令人印象深刻的结果。但是,它们很难使用,因为它们会受到手动制作的提示的高度可变性,并且通常需要十亿参数语言模型才能达到高精度。为了解决这些缺点,我们提出了SETFIT(句子变压器微调),这是一个有效且迅速的框架,用于对句子变形金刚(ST)进行几次微调。 SetFit首先以对比的暹罗方式对少数文本对进行微调验证的st。然后将所得模型用于生成丰富的文本嵌入,这些嵌入方式用于训练分类头。这个简单的框架不需要任何提示或口头化,并且比现有技术少的参数较少,因此可以实现高精度。我们的实验表明,SetFit通过PEFT和PET技术获得了可比的结果,同时训练的速度更快。我们还表明,SETFIT可以通过简单地切换ST主体来应用于多语言设置。我们的代码可从https://github.com/huggingface/setFit以及我们的数据集获得,网址为https://huggingface.co/setfit。
translated by 谷歌翻译
我们提出了一种整体方法,用于构建一个可实现的自然语言分类系统,以实现现实世界中的内容适度。这样一个系统的成功依赖于一系列精心设计和执行的步骤,包括内容分类法和标签说明的设计,数据质量控制,主动学习管道以捕获罕见事件以及使模型可靠的各种方法并避免过度拟合。我们的审核系统经过培训,可以检测一系列不希望的内容,包括性内容,可恨的内容,暴力,自我伤害和骚扰。这种方法概括为各种不同的内容分类法,可用于创建优于现成模型的高质量内容分类器。
translated by 谷歌翻译
最近的自然语言理解进展(NLU)已经被驱动,部分是由胶水,超级格,小队等的基准。事实上,许多NLU模型现在在许多任务中匹配或超过“人类水平”性能这些基准。然而,大多数这些基准测试都提供模型访问相对大量的标记数据进行培训。因此,该模型提供了比人类所需的更多数据,以实现强大的性能。这有动机侧重于侧重于改善NLU模型的少量学习性能。然而,缺乏少量射门的标准化评估基准,导致不同纸张中的不同实验设置。为了帮助加速这一工作的工作,我们介绍了线索(受限制的语言理解评估标准),这是评估NLU模型的几次拍摄学习功能的基准。我们证明,虽然最近的模型在获得大量标记数据时达到人类性能,但对于大多数任务,少量拍摄设置中的性能存在巨大差距。我们还展示了几个拍摄设置中替代模型家族和适应技术之间的差异。最后,我们讨论了在设计实验设置时讨论了评估真实少量学习绩效的实验设置,并提出了统一的标准化方法,以获得少量学习评估。我们的目标是鼓励对NLU模型的研究,可以概括为具有少数示例的新任务。线索的代码和数据可以在https://github.com/microsoft/clues提供。
translated by 谷歌翻译
少量学习时,基于及时的方法很强劲。然而,Perez等人。 (2021年)最近对他们的表现产生了疑问,因为它们难以在“真实”的几次拍摄设置中获得良好的结果,其中提示和超级参数无法在DEV集上调整。鉴于此,我们对PET进行了广泛的研究,该方法将文本指令与基于示例的FENETUNING结合起来。我们表明,如果正确配置,宠物在真正的几次拍摄设置中强烈执行,即,没有开发装置。这对这种强大的表现至关重要是宠物智能处理多个提示的能力。然后,我们通过在RAFT上运行PET来将我们的调查结果置于真实世界的测试中,直接从现实的NLP应用程序采取的任务的基准,没有标记的开发或测试集。宠物在筏上实现了新的艺术状态,并且在11个任务中靠近非专家人类进行了近距离进行。这些结果表明,基于及时的学习者像宠物Excel这样的真正的几次拍摄学习和支持我们的信念,即从指示中学习的信念将在人类少量学习能力的路径上发挥重要作用。
translated by 谷歌翻译
The recent GPT-3 model (Brown et al., 2020) achieves remarkable few-shot performance solely by leveraging a natural-language prompt and a few task demonstrations as input context. Inspired by their findings, we study few-shot learning in a more practical scenario, where we use smaller language models for which fine-tuning is computationally efficient. We present LM-BFF-better few-shot fine-tuning of language models 1 -a suite of simple and complementary techniques for finetuning language models on a small number of annotated examples. Our approach includes (1) prompt-based fine-tuning together with a novel pipeline for automating prompt generation; and (2) a refined strategy for dynamically and selectively incorporating demonstrations into each context. Finally, we present a systematic evaluation for analyzing few-shot performance on a range of NLP tasks, including classification and regression. Our experiments demonstrate that our methods combine to dramatically outperform standard fine-tuning procedures in this low resource setting, achieving up to 30% absolute improvement, and 11% on average across all tasks. Our approach makes minimal assumptions on task resources and domain expertise, and hence constitutes a strong task-agnostic method for few-shot learning. 2 * The first two authors contributed equally. 1 Alternatively, language models' best friends forever. 2 Our implementation is publicly available at https:// github.com/princeton-nlp/LM-BFF.
translated by 谷歌翻译
人工智能的最新趋势是将验证的模型用于语言和视觉任务,这些模型已经实现了非凡的表现,但也令人困惑。因此,以各种方式探索这些模型的能力对该领域至关重要。在本文中,我们探讨了模型的可靠性,在其中我们将可靠的模型定义为一个不仅可以实现强大的预测性能,而且在许多涉及不确定性(例如选择性预测,开放式设置识别)的决策任务上,在许多决策任务上表现出色,而且表现良好。强大的概括(例如,准确性和适当的评分规则,例如在分布数据集中和分发数据集上的对数可能性)和适应性(例如,主动学习,几乎没有射击不确定性)。我们设计了40个数据集的10种任务类型,以评估视觉和语言域上可靠性的不同方面。为了提高可靠性,我们分别开发了VIT-PLEX和T5-PLEX,分别针对视觉和语言方式扩展了大型模型。 PLEX极大地改善了跨可靠性任务的最先进,并简化了传统协议,因为它可以改善开箱即用的性能,并且不需要设计分数或为每个任务调整模型。我们演示了高达1B参数的模型尺寸的缩放效果,并预处理数据集大小最多4B示例。我们还展示了PLEX在具有挑战性的任务上的功能,包括零射门的开放式识别,主动学习和对话语言理解中的不确定性。
translated by 谷歌翻译
As an important data selection schema, active learning emerges as the essential component when iterating an Artificial Intelligence (AI) model. It becomes even more critical given the dominance of deep neural network based models, which are composed of a large number of parameters and data hungry, in application. Despite its indispensable role for developing AI models, research on active learning is not as intensive as other research directions. In this paper, we present a review of active learning through deep active learning approaches from the following perspectives: 1) technical advancements in active learning, 2) applications of active learning in computer vision, 3) industrial systems leveraging or with potential to leverage active learning for data iteration, 4) current limitations and future research directions. We expect this paper to clarify the significance of active learning in a modern AI model manufacturing process and to bring additional research attention to active learning. By addressing data automation challenges and coping with automated machine learning systems, active learning will facilitate democratization of AI technologies by boosting model production at scale.
translated by 谷歌翻译