Large-scale pretraining instills large amounts of knowledge in deep neural networks. This, in turn, improves the generalization behavior of these models in downstream tasks. What exactly are the limits to the generalization benefits of large-scale pretraining? Here, we report observations from some simple experiments aimed at addressing this question in the context of two semantic parsing tasks involving natural language, SCAN and COGS. We show that language models pretrained exclusively with non-English corpora, or even with programming language corpora, significantly improve out-of-distribution generalization in these benchmarks, compared with models trained from scratch, even though both benchmarks are English-based. This demonstrates the surprisingly broad transferability of pretrained representations and knowledge. Pretraining with a large-scale protein sequence prediction task, on the other hand, mostly deteriorates the generalization performance in SCAN and COGS, suggesting that pretrained representations do not transfer universally and that there are constraints on the similarity between the pretraining and downstream domains for successful transfer. Finally, we show that larger models are harder to train from scratch and their generalization accuracy is lower when trained up to convergence on the relatively small SCAN and COGS datasets, but the benefits of large-scale pretraining become much clearer with larger models.

在多语言甚至单语言中鉴定的模型的零拍跨语言能力刺激了许多假设，以解释这一有趣的经验结果。但是，由于预处理的成本，大多数研究都使用公共模型的公共模型，其预处理方法（例如代币化，语料库规模和计算预算的选择）可能会大不相同。当研究人员对自己的模型预识时，他们通常会在预算有限的情况下这样做，并且与SOTA模型相比，最终的模型的表现可能明显不足。这些实验差异导致有关这些模型跨语性能力的性质的各种不一致的结论。为了帮助对该主题进行进一步研究，我们发布了10个单语字节级模型，并在相同的配置下进行了严格审慎的概述，并具有大型计算预算（相当于V100的420天）和Corpora，比原始BERT大4倍。由于它们不含令牌，因此消除了看不见的令牌嵌入的问题，从而使研究人员可以在具有不同脚本的语言中尝试更广泛的跨语言实验。此外，我们释放了在不自然语言文本上预测的两个模型，这些模型可用于理智检查实验。关于质量检查和NLI任务的实验表明，我们的单语模型实现了多语言的竞争性能，因此可以加强我们对语言模型中跨语性可传递性的理解。

对于大多数自然语言处理任务，主要的实践是使用较小的下游数据集对大型预验证变压器模型（例如BERT）。尽管这种方法取得了成功，但尚不清楚这些收益在多大程度上归因于用于预处理而不是训练预处理的目标本身所采用的大量背景语料库。本文介绍了一项大规模的自我预测研究，其中相同的（下游）训练数据都用于预训练和填充。在解决Electra和Roberta型号以及10个不同下游数据集的实验中，我们观察到在BookWiki语料库上进行自我预测的竞争对手标准预告片（尽管使用了$ 10 \ times $ $ -500 \ times $ -500 \ times $少的数据），在7美元上以7美元的价格优于$ 7 $和$ 5 $数据集。令人惊讶的是，这些特定于任务的预预性模型通常在其他任务（包括胶水基准）上表现良好。我们的结果表明，在许多情况下，可归因于预处理的绩效收益主要是由预处理目标本身驱动的，并不总是归因于大规模数据集的合并。考虑到网络规模预处理数据中对知识产权和进攻内容的担忧，这些发现尤其重要。

Human linguistic capacity is often characterized by compositionality and the generalization it enables -- human learners can produce and comprehend novel complex expressions by composing known parts. Several benchmarks exploit distributional control across training and test to gauge compositional generalization, where certain lexical items only occur in limited contexts during training. While recent work using these benchmarks suggests that pretrained models achieve impressive generalization performance, we argue that exposure to pretraining data may break the aforementioned distributional control. Using the COGS benchmark of Kim and Linzen (2020), we test two modified evaluation setups that control for this issue: (1) substituting context-controlled lexical items with novel character sequences, and (2) substituting them with special tokens represented by novel embeddings. We find that both of these setups lead to lower generalization performance in T5 (Raffel et al., 2020), suggesting that previously reported results have been overestimated due to uncontrolled lexical exposure during pretraining. The performance degradation is more extreme with novel embeddings, and the degradation increases with the amount of pretraining data, highlighting an interesting case of inverse scaling.

神经网络模型通常概括到不匹配的域或分布不符。在NLP中，特别是当预期模型概括为合作的模型，即熟悉词汇和建筑的新组合时，尤其产生这个问题。我们调查促进从一个组成任务转移到另一个组成任务的学习的学习陈述：模型的代表和任务特定层在预先驾驶任务上具有不同的培训，使得它们概括为需要合成性的不匹配分裂。我们将此方法应用于语义解析，使用三个非常不同的数据集，COG，地理信息集和扫描，作为FineTuning和目标任务交替使用。我们的方法显着改善了在目标任务的测试组上的基线上的组成概括，在微调期间被列出。消融研究表征了所提出的算法中主要步骤的效用，并支持我们的假设。

在这项工作中，我们证明了多种语的大规模序列到序列（SEQ2SEQ）模型，该模型是通过Denoising和因果语言建模（CLM）任务的混合物进行训练的，比仅解码器模型更有效地进行了效率的学习者在各种任务上。特别是，我们培训了一个名为Alexa教师模型（Alexatm 20b）的200亿个参数多语言SEQ2SEQ模型，并表明它在1-Shot摘要任务上实现了最先进的（SOTA）性能，超过了更大的540B PALM DOPODER模型。 Alexatm 20b还可以在1-Shot Machine翻译中实现SOTA，尤其是对于低资源语言，几乎所有语言对（阿拉伯语，英语，法语，德语，德语，印地语，意大利语，日语，以及flores-101数据集上的泰卢固语）。我们还显示了零拍设置，AlexATM 20B在SuperGlue和SqueadV2数据集上的表现优于GPT3（175B），并在XNLI，XCOPA，PAWS-X和XWINOGRAD等多语言任务上提供SOTA性能。总体而言，我们的结果为SEQ2SEQ模型提供了一个令人信服的案例，作为大型语言模型（LLM）培训的仅解码器模型的强大替代方法。

有效的缩放和灵活的任务接口使大型语言模型能够在许多任务中表现出色。帕利（Pali）根据视觉和文本输入生成文本，并使用该界面以许多语言执行许多视觉，语言和多模式任务。为了训练帕利，我们利用了大型的编码器语言模型和视觉变压器（VITS）。这使我们能够利用其现有能力，并利用培训它们的大量成本。我们发现，视觉和语言组成部分的联合缩放很重要。由于现有的语言变压器比其视觉对应物要大得多，因此我们训练迄今为止最大的VIT（VIT-E），以量化甚至大容量视觉模型的好处。为了训练Pali，我们基于一个新的图像文本训练集，其中包含10B图像和文本，以100多种语言来创建大型的多语言组合。帕利（Pali）在多个视觉和语言任务（例如字幕，视觉问题，索方式，场景文本理解）中实现了最新的，同时保留了简单，模块化和可扩展的设计。

The BLOOM model is a large open-source multilingual language model capable of zero-shot learning, but its pretraining was limited to 46 languages. To improve its zero-shot performance on unseen languages, it is desirable to adapt BLOOM, but previous works have only explored adapting small language models. In this work, we apply existing language adaptation strategies to BLOOM and benchmark its zero-shot prompting performance on eight new languages. We find language adaptation to be effective at improving zero-shot performance in new languages. Surprisingly, adapter-based finetuning is more effective than continued pretraining for large models. In addition, we discover that prompting performance is not significantly affected by language specifics, such as the writing system. It is primarily determined by the size of the language adaptation data. We also add new languages to BLOOMZ, which is a multitask finetuned version of BLOOM capable of following task instructions zero-shot. We find including a new language in the multitask fine-tuning mixture to be the most effective method to teach BLOOMZ a new language. We conclude that with sufficient training data language adaptation can generalize well to diverse languages. Our code is available at \url{https://github.com/bigscience-workshop/multilingual-modeling/}.

Multimodal models are becoming increasingly effective, in part due to unified components, such as the Transformer architecture. However, multimodal models still often consist of many task- and modality-specific pieces and training procedures. For example, CLIP (Radford et al., 2021) trains independent text and image towers via a contrastive loss. We explore an additional unification: the use of a pure pixel-based model to perform image, text, and multimodal tasks. Our model is trained with contrastive loss alone, so we call it CLIP-Pixels Only (CLIPPO). CLIPPO uses a single encoder that processes both regular images and text rendered as images. CLIPPO performs image-based tasks such as retrieval and zero-shot image classification almost as well as CLIP, with half the number of parameters and no text-specific tower or embedding. When trained jointly via image-text contrastive learning and next-sentence contrastive learning, CLIPPO can perform well on natural language understanding tasks, without any word-level loss (language modelling or masked language modelling), outperforming pixel-based prior work. Surprisingly, CLIPPO can obtain good accuracy in visual question answering, simply by rendering the question and image together. Finally, we exploit the fact that CLIPPO does not require a tokenizer to show that it can achieve strong performance on multilingual multimodal retrieval without

多语言语言模型（\ mllms），如mbert，xlm，xlm-r，\ textit {etc。}已成为一种可行的选择，使预先估计到大量语言的力量。鉴于他们的成功在零射击转移学习中，在（i）建立更大的\ mllms〜覆盖了大量语言（ii）创建覆盖更广泛的任务和语言来评估的详尽工作基准mllms〜（iii）分析单音零点，零拍摄交叉和双语任务（iv）对Monolingual的性能，了解\ mllms〜（v）增强（通常）学习的通用语言模式（如果有的话）有限的容量\ mllms〜以提高他们在已见甚至看不见语言的表现。在这项调查中，我们审查了现有的文学，涵盖了上述与\ MLLMS有关的广泛研究领域。根据我们的调查，我们建议您有一些未来的研究方向。

本文探讨了提高语言模型的零次学习能力的简单方法。我们表明，指令调整 - 通过对说明书中所述的任务集合微调语言模型 - 大幅提升零射门上看不见任务中的表现。我们采取预训练的语言模型和指令调整它通过自然语言指令模板语言表达了60NLP任务137B参数。我们评估这种指令调整模型，我们称之为FLAN，在看不见的任务类型。FLAN显着改善其未修饰的对应的性能和超过25的20个任务，我们评估零射门175BGPT-3。FLAN甚至GPT-3通过在安利，RTE，BoolQ，AI2-ARC，OpenbookQA和StoryCloze大比分胜过几拍。消融研究显示任务和模型的规模，这个数字是指令调整取得成功的关键组成部分。

经过审计的多语言模型已成为将NLP功能转移到低资源语言的常见工具，通常具有适应性。在这项工作中，我们研究了两种改编的性能，可扩展性和相互作用：词汇增强和脚本音译。我们对九种多样化的低资源语言中的词性标签，普遍依赖解析的评估，并命名为实体识别，以维护这些方法的可行性，同时围绕如何最佳地将多语言模型适应低资源设置的新问题。

本文介绍了Okapi，用于自然语言的新数据集到可执行的Web应用程序编程接口（NL2API）。此数据集是英文，包含22,508个问题和9,019个独特的API呼叫，涵盖三个域。我们为NL2API定义了新的组成泛化任务，该任务探讨了在推理阶段中的培训中从简单API调用外推开的模型能力。此外，该模型必须生成正确执行的API调用，而不是与现有方法进行正确执行，该方法评估具有占位符值的查询。我们的数据集与大多数现有的组合语义解析数据集不同，因为它是一个非合成数据集，研究了低资源设置中的组成概括。 Okapi是创建现实数据集和基准的一步，用于研究与现有数据集和任务一起学习组成泛化。我们报告了在各种扫描和okapi数据集任务上培训的序列到序列基线模型的泛化能力。当从简单API调用概括到更复杂的API调用时，最佳模型可实现15 \％精确匹配的准确性。这突出了未来研究的一些挑战。 okapi数据集和任务在https://aka.ms/nl2api/data上公开使用。

预处理的多语言上下文表示表现出了巨大的成功，但是由于其预处理数据的限制，其好处并不适用于所有语言品种。这给这些模型不熟悉的语言品种带来了挑战，这些模型的标签\ emph {和未标记的}数据太限制了无法有效训练单语模型。我们建议使用其他特定于语言的预审进和词汇增强，以使多语言模型适应低资源设置。使用依赖性解析四种不同的低资源语言品种作为案例研究，我们表明，这些方法显着改善了基准的性能，尤其是在最低的资源案例中，并证明了此类模型的数据和目标之间关系的重要性语言品种。

Transfer learning, where a model is first pre-trained on a data-rich task before being finetuned on a downstream task, has emerged as a powerful technique in natural language processing (NLP). The effectiveness of transfer learning has given rise to a diversity of approaches, methodology, and practice. In this paper, we explore the landscape of transfer learning techniques for NLP by introducing a unified framework that converts all text-based language problems into a text-to-text format. Our systematic study compares pre-training objectives, architectures, unlabeled data sets, transfer approaches, and other factors on dozens of language understanding tasks. By combining the insights from our exploration with scale and our new "Colossal Clean Crawled Corpus", we achieve state-of-the-art results on many benchmarks covering summarization, question answering, text classification, and more. To facilitate future work on transfer learning for NLP, we release our data set, pre-trained models, and code.

In this work, we explore "prompt tuning," a simple yet effective mechanism for learning "soft prompts" to condition frozen language models to perform specific downstream tasks. Unlike the discrete text prompts used by GPT-3, soft prompts are learned through backpropagation and can be tuned to incorporate signals from any number of labeled examples. Our end-to-end learned approach outperforms GPT-3's few-shot learning by a large margin. More remarkably, through ablations on model size using T5, we show that prompt tuning becomes more competitive with scale: as models exceed billions of parameters, our method "closes the gap" and matches the strong performance of model tuning (where all model weights are tuned). This finding is especially relevant because large models are costly to share and serve and the ability to reuse one frozen model for multiple downstream tasks can ease this burden. Our method can be seen as a simplification of the recently proposed "prefix tuning" of Li and Liang (2021) and we provide a comparison to this and other similar approaches. Finally, we show that conditioning a frozen model with soft prompts confers benefits in robustness to domain transfer and enables efficient "prompt ensembling." * Work done as a Google AI Resident.

基础模型由于在广泛的下游应用中的有效性而受到了很多关注。尽管在体系结构方面存在很大的融合，但大多数审慎的模型通常仍用于特定任务或模式。在这项工作中，我们建议将语言模型用作各种基础模型的通用接口。一系列预处理的编码者感知到了多种方式（例如视觉和语言），并与扮演通用任务层角色的语言模型对接。我们提出了一个半伴侣的语言建模目标，以共同确定界面和模块化编码器。我们从因果关系和非因果建模中涵盖了优势和能力，从而结合了两个世界的最佳状态。具体而言，所提出的方法不仅从因果语言建模中继承了内在学习和开放式生成的能力，而且由于双向编码器而有利于填补。更重要的是，我们的方法无缝地解锁了上述功能的组合，例如，通过填充编码器启用了文本学习或指导。各种仅语言和视觉语言基准的实验结果表明，我们的模型表现优于或与鉴定，零弹性概括和几乎没有的学习的专业模型竞争。

As the complexity of modern software continues to escalate, software engineering has become an increasingly daunting and error-prone endeavor. In recent years, the field of Neural Code Intelligence (NCI) has emerged as a promising solution, leveraging the power of deep learning techniques to tackle analytical tasks on source code with the goal of improving programming efficiency and minimizing human errors within the software industry. Pretrained language models have become a dominant force in NCI research, consistently delivering state-of-the-art results across a wide range of tasks, including code summarization, generation, and translation. In this paper, we present a comprehensive survey of the NCI domain, including a thorough review of pretraining techniques, tasks, datasets, and model architectures. We hope this paper will serve as a bridge between the natural language and programming language communities, offering insights for future research in this rapidly evolving field.

Software engineers working with the same programming language (PL) may speak different natural languages (NLs) and vice versa, erecting huge barriers to communication and working efficiency. Recent studies have demonstrated the effectiveness of generative pre-training in computer programs, yet they are always English-centric. In this work, we step towards bridging the gap between multilingual NLs and multilingual PLs for large language models (LLMs). We release ERNIE-Code, a unified pre-trained language model for 116 NLs and 6 PLs. We employ two methods for universal cross-lingual pre-training: span-corruption language modeling that learns patterns from monolingual NL or PL; and pivot-based translation language modeling that relies on parallel data of many NLs and PLs. Extensive results show that ERNIE-Code outperforms previous multilingual LLMs for PL or NL across a wide range of end tasks of code intelligence, including multilingual code-to-text, text-to-code, code-to-code, and text-to-text generation. We further show its advantage of zero-shot prompting on multilingual code summarization and text-to-text translation. We will make our code and pre-trained models publicly available.

Transformer language models (TLMs) are critical for most NLP tasks, but they are difficult to create for low-resource languages because of how much pretraining data they require. In this work, we investigate two techniques for training monolingual TLMs in a low-resource setting: greatly reducing TLM size, and complementing the masked language modeling objective with two linguistically rich supervised tasks (part-of-speech tagging and dependency parsing). Results from 7 diverse languages indicate that our model, MicroBERT, is able to produce marked improvements in downstream task evaluations relative to a typical monolingual TLM pretraining approach. Specifically, we find that monolingual MicroBERT models achieve gains of up to 18% for parser LAS and 11% for NER F1 compared to a multilingual baseline, mBERT, while having less than 1% of its parameter count. We conclude reducing TLM parameter count and using labeled data for pretraining low-resource TLMs can yield large quality benefits and in some cases produce models that outperform multilingual approaches.