Improving Language Understanding by Generative Pre-Training

通过生成式预训练提升语言理解能力

Alec Radford Karthik Narasimhan Tim Salimans Ilya Sutskever OpenAI OpenAI OpenAI OpenAI alec@openai.com karthikn@openai.com tim@openai.com ilyasu@openai.com

Abstract

摘要

Natural language understanding comprises a wide range of diverse tasks such as textual entailment, question answering, semantic similarity assessment, and document classification. Although large unlabeled text corpora are abundant, labeled data for learning these specific tasks is scarce, making it challenging for disc rim i natively trained models to perform adequately. We demonstrate that large gains on these tasks can be realized by generative pre-training of a language model on a diverse corpus of unlabeled text, followed by disc rim i native fine-tuning on each specific task. In contrast to previous approaches, we make use of task-aware input transformations during fine-tuning to achieve effective transfer while requiring minimal changes to the model architecture. We demonstrate the effectiveness of our approach on a wide range of benchmarks for natural language understanding. Our general task-agnostic model outperforms disc rim i natively trained models that use architectures specifically crafted for each task, significantly improving upon the state of the art in 9 out of the 12 tasks studied. For instance, we achieve absolute improvements of $8.9%$ on commonsense reasoning (Stories Cloze Test), $5.7%$ on question answering (RACE), and $1.5%$ on textual entailment (MultiNLI).

自然语言理解涵盖了多种多样的任务，如文本蕴含、问答、语义相似度评估和文档分类。尽管大量未标注的文本语料库很丰富，但用于学习这些特定任务的标注数据却很稀缺，这使得判别式训练的模型难以充分执行这些任务。我们展示了通过对未标注文本的多样化语料库进行生成式预训练，然后在每个特定任务上进行判别式微调，可以在这些任务上实现显著的提升。与之前的方法不同，我们在微调过程中利用任务感知的输入转换，以实现有效的迁移，同时只需对模型架构进行最小的更改。我们在自然语言理解的广泛基准测试中展示了我们方法的有效性。我们的通用任务无关模型优于为每个任务专门设计的判别式训练模型，在研究的12个任务中有9个显著改进了现有技术水平。例如，我们在常识推理（Stories Cloze Test）上实现了8.9%的绝对提升，在问答（RACE）上实现了5.7%的提升，在文本蕴含（MultiNLI）上实现了1.5%的提升。

1 Introduction

1 引言

The ability to learn effectively from raw text is crucial to alleviating the dependence on supervised learning in natural language processing (NLP). Most deep learning methods require substantial amounts of manually labeled data, which restricts their applicability in many domains that suffer from a dearth of annotated resources [61]. In these situations, models that can leverage linguistic information from unlabeled data provide a valuable alternative to gathering more annotation, which can be time-consuming and expensive. Further, even in cases where considerable supervision is available, learning good representations in an unsupervised fashion can provide a significant performance boost. The most compelling evidence for this so far has been the extensive use of pretrained word embeddings [10, 39, 42] to improve performance on a range of NLP tasks [8, 11, 26, 45].

从原始文本中有效学习的能力对于减轻自然语言处理 (NLP) 中对监督学习的依赖至关重要。大多数深度学习方法需要大量手动标记的数据，这限制了它们在许多缺乏注释资源的领域中的适用性 [61]。在这些情况下，能够从未标记数据中利用语言信息的模型为收集更多注释提供了一种有价值的替代方案，而收集注释可能既耗时又昂贵。此外，即使在有大量监督可用的情况下，以无监督的方式学习良好的表示也可以显著提高性能。迄今为止，最有力的证据是广泛使用预训练的词嵌入 [10, 39, 42] 来提高一系列 NLP 任务的性能 [8, 11, 26, 45]。

Leveraging more than word-level information from unlabeled text, however, is challenging for two main reasons. First, it is unclear what type of optimization objectives are most effective at learning text representations that are useful for transfer. Recent research has looked at various objectives such as language modeling [44], machine translation [38], and discourse coherence [22], with each method outperforming the others on different tasks.1 Second, there is no consensus on the most effective way to transfer these learned representations to the target task. Existing techniques involve a combination of making task-specific changes to the model architecture [43, 44], using intricate learning schemes [21] and adding auxiliary learning objectives [50]. These uncertainties have made it difficult to develop effective semi-supervised learning approaches for language processing.

然而，从未标注文本中利用超过词级别的信息具有挑战性，主要有两个原因。首先，尚不清楚哪种类型的优化目标在学习对迁移有用的文本表示方面最为有效。最近的研究探讨了各种目标，如语言建模 [44]、机器翻译 [38] 和语篇连贯性 [22]，每种方法在不同任务上表现优于其他方法。其次，关于如何将这些学习到的表示迁移到目标任务中，目前尚无共识。现有技术包括对模型架构进行任务特定的修改 [43, 44]、使用复杂的学习方案 [21] 以及添加辅助学习目标 [50]。这些不确定性使得开发有效的语言处理半监督学习方法变得困难。

In this paper, we explore a semi-supervised approach for language understanding tasks using a combination of unsupervised pre-training and supervised fine-tuning. Our goal is to learn a universal representation that transfers with little adaptation to a wide range of tasks. We assume access to a large corpus of unlabeled text and several datasets with manually annotated training examples (target tasks). Our setup does not require these target tasks to be in the same domain as the unlabeled corpus. We employ a two-stage training procedure. First, we use a language modeling objective on the unlabeled data to learn the initial parameters of a neural network model. Subsequently, we adapt these parameters to a target task using the corresponding supervised objective.

在本文中，我们探索了一种结合无监督预训练和有监督微调的半监督方法，用于语言理解任务。我们的目标是学习一种通用表示，该表示只需少量适应即可迁移到广泛的任务中。我们假设可以访问大量未标注文本语料库和几个带有手动标注训练示例的数据集（目标任务）。我们的设置不要求这些目标任务与未标注语料库处于同一领域。我们采用了两阶段训练过程。首先，我们在未标注数据上使用语言建模目标来学习神经网络模型的初始参数。随后，我们使用相应的有监督目标将这些参数适应到目标任务中。

For our model architecture, we use the Transformer [62], which has been shown to perform strongly on various tasks such as machine translation [62], document generation [34], and syntactic parsing [29]. This model choice provides us with a more structured memory for handling long-term dependencies in text, compared to alternatives like recurrent networks, resulting in robust transfer performance across diverse tasks. During transfer, we utilize task-specific input adaptations derived from traversal-style approaches [52], which process structured text input as a single contiguous sequence of tokens. As we demonstrate in our experiments, these adaptations enable us to fine-tune effectively with minimal changes to the architecture of the pre-trained model.

在我们的模型架构中，我们使用了 Transformer [62]，该模型在机器翻译 [62]、文档生成 [34] 和句法解析 [29] 等各种任务中表现出色。与循环网络等替代方案相比，这种模型选择为我们提供了更结构化的记忆，以处理文本中的长期依赖关系，从而在不同任务中实现稳健的迁移性能。在迁移过程中，我们利用了基于遍历式方法 [52] 的任务特定输入适配，这些方法将结构化文本输入处理为单个连续的 token 序列。正如我们在实验中所展示的，这些适配使我们能够在对预训练模型的架构进行最小改动的情况下，有效地进行微调。

We evaluate our approach on four types of language understanding tasks – natural language inference, question answering, semantic similarity, and text classification. Our general task-agnostic model outperforms disc rim i natively trained models that employ architectures specifically crafted for each task, significantly improving upon the state of the art in 9 out of the 12 tasks studied. For instance, we achieve absolute improvements of $8.9%$ on commonsense reasoning (Stories Cloze Test) [40], $5.7%$ on question answering (RACE) [30], $1.5%$ on textual entailment (MultiNLI) [66] and $5.5%$ on the recently introduced GLUE multi-task benchmark [64]. We also analyzed zero-shot behaviors of the pre-trained model on four different settings and demonstrate that it acquires useful linguistic knowledge for downstream tasks.

我们在四种类型的语言理解任务上评估了我们的方法——自然语言推理、问答、语义相似度和文本分类。我们的通用任务无关模型优于为每个任务专门设计的架构的判别训练模型，在研究的12个任务中有9个显著提升了现有技术水平。例如，我们在常识推理（Stories Cloze Test）[40]上实现了8.9%的绝对提升，在问答（RACE）[30]上实现了5.7%的绝对提升，在文本蕴含（MultiNLI）[66]上实现了1.5%的绝对提升，在最近引入的GLUE多任务基准[64]上实现了5.5%的绝对提升。我们还分析了预训练模型在四种不同设置下的零样本行为，并证明它为下游任务获取了有用的语言知识。

2 Related Work

2 相关工作

Semi-supervised learning for NLP Our work broadly falls under the category of semi-supervised learning for natural language. This paradigm has attracted significant interest, with applications to tasks like sequence labeling [24, 33, 57] or text classification [41, 70]. The earliest approaches used unlabeled data to compute word-level or phrase-level statistics, which were then used as features in a supervised model [33]. Over the last few years, researchers have demonstrated the benefits of using word embeddings [11, 39, 42], which are trained on unlabeled corpora, to improve performance on a variety of tasks [8, 11, 26, 45]. These approaches, however, mainly transfer word-level information, whereas we aim to capture higher-level semantics.

自然语言处理中的半监督学习

我们的工作大致属于自然语言处理中的半监督学习范畴。这一范式引起了广泛关注，并应用于序列标注 [24, 33, 57] 或文本分类 [41, 70] 等任务。最早的方法使用未标注数据来计算词级或短语级的统计信息，然后将这些信息作为监督模型中的特征 [33]。在过去几年中，研究人员展示了使用在未标注语料库上训练的词嵌入 [11, 39, 42] 来提升各种任务性能的优势 [8, 11, 26, 45]。然而，这些方法主要传递词级信息，而我们的目标是捕捉更高层次的语义。

Recent approaches have investigated learning and utilizing more than word-level semantics from unlabeled data. Phrase-level or sentence-level embeddings, which can be trained using an unlabeled corpus, have been used to encode text into suitable vector representations for various target tasks [28, 32, 1, 36, 22, 12, 56, 31].

最近的研究方法探索了从未标注数据中学习和利用超越词级别的语义。短语级别或句子级别的嵌入可以通过未标注的语料库进行训练，并用于将文本编码为适合各种目标任务的向量表示 [28, 32, 1, 36, 22, 12, 56, 31]。

Unsupervised pre-training Unsupervised pre-training is a special case of semi-supervised learning where the goal is to find a good initialization point instead of modifying the supervised learning objective. Early works explored the use of the technique in image classification [20, 49, 63] and regression tasks [3]. Subsequent research [15] demonstrated that pre-training acts as a regular iz ation scheme, enabling better generalization in deep neural networks. In recent work, the method has been used to help train deep neural networks on various tasks like image classification [69], speech recognition [68], entity disambiguation [17] and machine translation [48].

无监督预训练
无监督预训练是半监督学习的一种特殊情况，其目标是找到一个好的初始化点，而不是修改监督学习的目标。早期的工作探索了该技术在图像分类 [20, 49, 63] 和回归任务 [3] 中的应用。后续研究 [15] 表明，预训练作为一种正则化方案，能够在深度神经网络中实现更好的泛化。在最近的研究中，该方法被用于帮助训练深度神经网络完成各种任务，如图像分类 [69]、语音识别 [68]、实体消歧 [17] 和机器翻译 [48]。

The closest line of work to ours involves pre-training a neural network using a language modeling objective and then fine-tuning it on a target task with supervision. Dai et al. [13] and Howard and Ruder [21] follow this method to improve text classification. However, although the pre-training phase helps capture some linguistic information, their usage of LSTM models restricts their prediction ability to a short range. In contrast, our choice of transformer networks allows us to capture longerrange linguistic structure, as demonstrated in our experiments. Further, we also demonstrate the effectiveness of our model on a wider range of tasks including natural language inference, paraphrase detection and story completion. Other approaches [43, 44, 38] use hidden representations from a pre-trained language or machine translation model as auxiliary features while training a supervised model on the target task. This involves a substantial amount of new parameters for each separate target task, whereas we require minimal changes to our model architecture during transfer.

与我们工作最接近的研究涉及使用语言建模目标预训练神经网络，然后在有监督的目标任务上进行微调。Dai 等人 [13] 以及 Howard 和 Ruder [21] 采用这种方法来改进文本分类。然而，尽管预训练阶段有助于捕捉一些语言信息，但他们使用的 LSTM 模型限制了其预测能力的范围。相比之下，我们选择的 Transformer 网络使我们能够捕捉更远距离的语言结构，正如我们的实验所展示的那样。此外，我们还在更广泛的任务上展示了我们模型的有效性，包括自然语言推理、释义检测和故事补全。其他方法 [43, 44, 38] 使用来自预训练语言或机器翻译模型的隐藏表示作为辅助特征，同时在目标任务上训练有监督的模型。这需要为每个单独的目标任务引入大量新参数，而我们在迁移过程中对模型架构的改动非常小。

Auxiliary training objectives Adding auxiliary unsupervised training objectives is an alternative form of semi-supervised learning. Early work by Collobert and Weston [10] used a wide variety of auxiliary NLP tasks such as POS tagging, chunking, named entity recognition, and language modeling to improve semantic role labeling. More recently, Rei [50] added an auxiliary language modeling objective to their target task objective and demonstrated performance gains on sequence labeling tasks. Our experiments also use an auxiliary objective, but as we show, unsupervised pre-training already learns several linguistic aspects relevant to target tasks.

辅助训练目标
添加辅助无监督训练目标是半监督学习的另一种形式。Collobert 和 Weston [10] 的早期工作使用了多种辅助 NLP 任务，如词性标注 (POS tagging)、分块 (chunking)、命名实体识别 (named entity recognition) 和语言建模 (language modeling)，以改进语义角色标注 (semantic role labeling)。最近，Rei [50] 在其目标任务目标中添加了辅助语言建模目标，并在序列标注任务中展示了性能提升。我们的实验也使用了辅助目标，但正如我们所展示的，无监督预训练已经学习了与目标任务相关的多个语言方面。

3 Framework

3 框架

Our training procedure consists of two stages. The first stage is learning a high-capacity language model on a large corpus of text. This is followed by a fine-tuning stage, where we adapt the model to a disc rim i native task with labeled data.

我们的训练过程包括两个阶段。第一阶段是在大量文本语料库上学习一个高容量的语言模型。随后是微调阶段，在这个阶段中，我们使用标注数据将模型适配到一个判别任务上。

3.1 Unsupervised pre-training

3.1 无监督预训练

Given an unsupervised corpus of tokens $\mathcal{U}={u_{1},\ldots,u_{n}}$ , we use a standard language modeling objective to maximize the following likelihood:

给定一个无监督的 Token 语料库 $\mathcal{U}={u_{1},\ldots,u_{n}}$，我们使用标准的语言建模目标来最大化以下似然：

$$
L_{1}(\mathcal{U})=\sum_{i}\log P(u_{i}|u_{i-k},\ldots,u_{i-1};\Theta)
$$

$$
L_{1}(\mathcal{U})=\sum_{i}\log P(u_{i}|u_{i-k},\ldots,u_{i-1};\Theta)
$$

where $k$ is the size of the context window, and the conditional probability $P$ is modeled using a neural network with parameters $\Theta$ . These parameters are trained using stochastic gradient descent [51].

其中 $k$ 是上下文窗口的大小，条件概率 $P$ 使用参数为 $\Theta$ 的神经网络建模。这些参数通过随机梯度下降法 [51] 进行训练。

In our experiments, we use a multi-layer Transformer decoder [34] for the language model, which is a variant of the transformer [62]. This model applies a multi-headed self-attention operation over the input context tokens followed by position-wise feed forward layers to produce an output distribution over target tokens:

在我们的实验中，我们使用了一个多层Transformer解码器[34]作为语言模型，这是Transformer[62]的一个变体。该模型在输入上下文Token上应用多头自注意力操作，然后通过逐位置的前馈层生成目标Token的输出分布：

$$
\begin{array}{r l}&{h_{0}=U W_{e}+W_{p}}\ &{\quad h_{l}=\mathsf{t r a n s f o r m e r_b l o c k}(h_{l-1})\forall i\in[1,n]}\ &{P(u)=\mathsf{s o f,t m a x}(h_{n}W_{e}^{T})}\end{array}
$$

$$
\begin{array}{r l}&{h_{0}=U W_{e}+W_{p}}\ &{\quad h_{l}=\mathsf{t r a n s f o r m e r_b l o c k}(h_{l-1})\forall i\in[1,n]}\ &{P(u)=\mathsf{s o f,t m a x}(h_{n}W_{e}^{T})}\end{array}
$$

where $U=(u_{-k},\dotsc,u_{-1})$ is the context vector of tokens, $n$ is the number of layers, $W_{e}$ is the token embedding matrix, and $W_{p}$ is the position embedding matrix.

其中 $U=(u_{-k},\dotsc,u_{-1})$ 是 Token 的上下文向量，$n$ 是层数，$W_{e}$ 是 Token 嵌入矩阵，$W_{p}$ 是位置嵌入矩阵。

3.2 Supervised fine-tuning

3.2 监督微调

After training the model with the objective in Eq. 1, we adapt the parameters to the supervised target task. We assume a labeled dataset $\mathcal{C}$ , where each instance consists of a sequence of input tokens, $x^{1},\ldots,x^{m}$ , along with a label $y$ . The inputs are passed through our pre-trained model to obtain the final transformer block’s activation $h_{l}^{m}$ , which is then fed into an added linear output layer with parameters $W_{y}$ to predict $y$ :

在使用公式 1 中的目标训练模型后，我们将参数调整到有监督的目标任务上。我们假设有一个带标签的数据集 $\mathcal{C}$，其中每个实例由一系列输入 Token $x^{1},\ldots,x^{m}$ 和一个标签 $y$ 组成。输入通过我们的预训练模型传递，以获得最终 Transformer 块的激活 $h_{l}^{m}$，然后将其输入到一个带有参数 $W_{y}$ 的线性输出层中以预测 $y$：

$$
P(y|x^{1},\ldots,x^{m})=\mathsf{s o f t m a x}(h_{l}^{m}W_{y}).
$$

$$
P(y|x^{1},\ldots,x^{m})=\mathsf{s o f t m a x}(h_{l}^{m}W_{y}).
$$

This gives us the following objective to maximize:

这为我们提供了以下需要最大化的目标：

$$
L_{2}(\mathcal{C})=\sum_{(x,y)}\log P(y|x^{1},\ldots,x^{m}).
$$

$$
L_{2}(\mathcal{C})=\sum_{(x,y)}\log P(y|x^{1},\ldots,x^{m}).
$$

We additionally found that including language modeling as an auxiliary objective to the fine-tuning helped learning by (a) improving generalization of the supervised model, and (b) accelerating convergence. This is in line with prior work [50, 43], who also observed improved performance with such an auxiliary objective. Specifically, we optimize the following objective (with weight $\lambda$ ):

此外，我们发现将语言建模作为微调的辅助目标有助于学习，具体表现在：(a) 提高了监督模型的泛化能力，(b) 加速了收敛。这与之前的工作 [50, 43] 一致，他们也观察到使用这种辅助目标可以提升性能。具体来说，我们优化了以下目标（权重为 $\lambda$）：

$$
L_{3}(\mathcal{C})=L_{2}(\mathcal{C})+\lambda*L_{1}(\mathcal{C})
$$

$$
L_{3}(\mathcal{C})=L_{2}(\mathcal{C})+\lambda*L_{1}(\mathcal{C})
$$

Overall, the only extra parameters we require during fine-tuning are $W_{y}$ , and embeddings for delimiter tokens (described below in Section 3.3).

总体而言，我们在微调过程中唯一需要的额外参数是 $W_{y}$，以及分隔符 Token 的嵌入（在下面的第 3.3 节中描述）。

Figure 1: (left) Transformer architecture and training objectives used in this work. (right) Input transformations for fine-tuning on different tasks. We convert all structured inputs into token sequences to be processed by our pre-trained model, followed by a linear+softmax layer.

图 1: (左) 本工作中使用的 Transformer 架构和训练目标。(右) 针对不同任务进行微调的输入转换。我们将所有结构化输入转换为 Token 序列，由预训练模型处理，然后通过线性+softmax层。

3.3 Task-specific input transformations

3.3 任务特定的输入转换

For some tasks, like text classification, we can directly fine-tune our model as described above. Certain other tasks, like question answering or textual entailment, have structured inputs such as ordered sentence pairs, or triplets of document, question, and answers. Since our pre-trained model was trained on contiguous sequences of text, we require some modifications to apply it to these tasks. Previous work proposed learning task specific architectures on top of transferred representations [44]. Such an approach re-introduces a significant amount of task-specific customization and does not use transfer learning for these additional architectural components. Instead, we use a traversal-style approach [52], where we convert structured inputs into an ordered sequence that our pre-trained model can process. These input transformations allow us to avoid making extensive changes to the architecture across tasks. We provide a brief description of these input transformations below and Figure 1 provides a visual illustration. All transformations include adding randomly initialized start and end tokens $(\langle s\rangle,\langle e\rangle)$ .

对于某些任务，如文本分类，我们可以直接按照上述方法对模型进行微调。其他一些任务，如问答或文本蕴含，具有结构化的输入，例如有序的句子对，或文档、问题和答案的三元组。由于我们的预训练模型是在连续的文本序列上训练的，因此需要对其进行一些修改才能应用于这些任务。之前的工作提出了在迁移表示的基础上学习任务特定的架构 [44]。这种方法重新引入了大量的任务特定定制，并且没有对这些额外的架构组件使用迁移学习。相反，我们使用了一种遍历式方法 [52]，将结构化输入转换为预训练模型可以处理的有序序列。这些输入转换使我们能够避免在任务之间对架构进行大量更改。我们在下面简要描述了这些输入转换，图 1 提供了可视化说明。所有转换都包括添加随机初始化的起始和结束标记 $(\langle s\rangle,\langle e\rangle)$。

Textual entailment For entailment tasks, we concatenate the premise $p$ and hypothesis $h$ token sequences, with a delimiter token $(\mathfrak{G})$ in between.

文本蕴含
对于蕴含任务，我们将前提 $p$ 和假设 $h$ 的 Token 序列连接起来，并在中间加上一个分隔符 Token $(\mathfrak{G})$。

Similarity For similarity tasks, there is no inherent ordering of the two sentences being compared. To reflect this, we modify the input sequence to contain both possible sentence orderings (with a delimiter in between) and process each independently to produce two sequence representations $h_{l}^{m}$ which are added element-wise before being fed into the linear output layer.

相似性
对于相似性任务，被比较的两个句子没有固有的顺序。为了反映这一点，我们修改输入序列以包含两种可能的句子顺序（中间用分隔符隔开），并分别处理以生成两个序列表示 $h_{l}^{m}$，在输入线性输出层之前将它们按元素相加。

Question Answering and Commonsense Reasoning For these tasks, we are given a context document $z$ , a question $q$ , and a set of possible answers $\left{a_{k}\right}$ . We concatenate the document context and question with each possible answer, adding a delimiter token in between to get $\left[z;q;\mathbb{5};a_{k}\right]$ . Each of these sequences are processed independently with our model and then normalized via a softmax layer to produce an output distribution over possible answers.

问答与常识推理任务

在这些任务中，我们给定一个上下文文档 $z$，一个问题 $q$，以及一组可能的答案 $\left{a_{k}\right}$。我们将文档上下文和问题与每个可能的答案连接起来，并在中间添加一个分隔符 Token，得到 $\left[z;q;\mathbb{5};a_{k}\right]$。这些序列中的每一个都通过我们的模型独立处理，然后通过 softmax 层进行归一化，以生成可能答案的输出分布。

4 Experiments

4 实验

4.1 Setup

4.1 设置

Unsupervised pre-training We use the Books Corpus dataset [71] for training the language model. It contains over 7,000 unique unpublished books from a variety of genres including Adventure, Fantasy, and Romance. Crucially, it contains long stretches of contiguous text, which allows the generative model to learn to condition on long-range information. An alternative dataset, the 1B Word Benchmark, which is used by a similar approach, ELMo [44], is approximately the same size but is shuffled at a sentence level - destroying long-range structure. Our language model achieves a very low token level perplexity of 18.4 on this corpus.

无监督预训练 我们使用 Books Corpus 数据集 [71] 来训练语言模型。该数据集包含超过 7,000 本独特的未出版书籍，涵盖冒险、奇幻和爱情等多种类型。关键的是，它包含大量连续的文本，这使得生成模型能够学习如何基于长距离信息进行条件生成。另一种数据集 1B Word Benchmark 被类似的方法 ELMo [44] 使用，其规模大致相同，但在句子级别被打乱，破坏了长距离结构。我们的语言模型在该语料库上实现了非常低的 Token 级别困惑度，仅为 18.4。

Table 1: A list of the different tasks and datasets used in our experiments.

表 1: 实验中使用的不同任务和数据集列表。

任务	数据集
自然语言推理	SNLI [5], MultiNLI [66], Question NLI [64], RTE [4], SciTail [25]
问答	RACE [30], Story Cloze [40]
句子相似度	MSRParaphrase Corpus [14], Quora QuestionPairs [9], STSBenchmark [6]
分类	StanfordSentimentTreebank-2 [54], CoLA [65]

Model specifications Our model largely follows the original transformer work [62]. We trained a 12-layer decoder-only transformer with masked self-attention heads (768 dimensional states and 12 attention heads). For the position-wise feed-forward networks, we used 3072 dimensional inner states. We used the Adam optimization scheme [27] with a max learning rate of $2.5\mathrm{e-4}$ . The learning rate was increased linearly from zero over the first 2000 updates and annealed to 0 using a cosine schedule. We train for 100 epochs on mini batches of 64 randomly sampled, contiguous sequences of 512 tokens. Since layernorm [2] is used extensively throughout the model, a simple weight initialization of $N(0,0.02)$ was sufficient. We used a bytepair encoding (BPE) vocabulary with 40,000 merges [53] and residual, embedding, and attention dropouts with a rate of 0.1 for regular iz ation. We also employed a modified version of L2 regular iz ation proposed in [37], with $w=0.01$ on all non bias or gain weights. For the activation function, we used the Gaussian Error Linear Unit (GELU) [18]. We used learned position embeddings instead of the sinusoidal version proposed in the original work. We use the ftfy library2 to clean the raw text in Books Corpus, standardize some punctuation and whitespace, and use the spaCy tokenizer.3

模型规格

我们的模型主要遵循了原始 Transformer 工作 [62]。我们训练了一个 12 层的仅解码器 Transformer，带有掩码自注意力头（768 维状态和 12 个注意力头）。对于位置前馈网络，我们使用了 3072 维的内部状态。我们使用了 Adam 优化方案 [27]，最大学习率为 $2.5\mathrm{e-4}$。学习率在前 2000 次更新中从零线性增加，并使用余弦调度退火至 0。我们在 64 个随机采样的连续 512 个 Token 的小批量上训练了 100 个周期。由于在整个模型中广泛使用了 layernorm [2]，因此简单的权重初始化 $N(0,0.02)$ 就足够了。我们使用了 40,000 次合并的字节对编码 (BPE) 词汇表 [53]，以及残差、嵌入和注意力 dropout，正则化率为 0.1。我们还采用了 [37] 中提出的修改版 L2 正则化，对所有非偏置或增益权重使用 $w=0.01$。对于激活函数，我们使用了高斯误差线性单元 (GELU) [18]。我们使用了学习的位置嵌入，而不是原始工作中提出的正弦版本。我们使用 ftfy 库来清理 Books Corpus 中的原始文本，标准化一些标点符号和空格，并使用 spaCy 分词器。

Fine-tuning details Unless specified, we reuse the hyper parameter settings from unsupervised pre-training. We add dropout to the classifier with a rate of 0.1. For most tasks, we use a learning rate of $6.25\mathrm{e}{-5}$ and a batchsize of 32. Our model finetunes quickly and 3 epochs of training was sufficient for most cases. We use a linear learning rate decay schedule with warmup over $0.2%$ of training. $\lambda$ was set to 0.5.

微调细节
除非另有说明，我们复用无监督预训练的超参数设置。我们在分类器中添加了 dropout，比例为 0.1。对于大多数任务，我们使用学习率为 $6.25\mathrm{e}{-5}$，批量大小为 32。我们的模型微调速度很快，大多数情况下 3 个训练周期就足够了。我们使用线性学习率衰减计划，并在 $0.2%$ 的训练过程中进行预热。$\lambda$ 设置为 0.5。

4.2 Supervised fine-tuning

4.2 监督微调

We perform experiments on a variety of supervised tasks including natural language inference, question answering, semantic similarity, and text classification. Some of these tasks are available as part of the recently released GLUE multi-task benchmark [64], which we make use of. Figure 1 provides an overview of all the tasks and datasets.

我们在多种监督任务上进行了实验，包括自然语言推理、问答、语义相似度和文本分类。其中一些任务来自最近发布的 GLUE 多任务基准 [64]，我们利用了这些任务。图 1 提供了所有任务和数据集的概览。

Natural Language Inference The task of natural