The denoising autoencoding objective is utilized to train encoder-decoder models by requiring them to reconstruct an original, uncorrupted sequence from a corrupted input. Operating similarly to a denoising autoencoder, the encoder processes the corrupted input—such as a sequence with masked tokens—and transforms it into a hidden representation. The decoder then uses this hidden representation to predict the original text. By learning to map a corrupted sequence to its uncorrupted counterpart, the model concurrently develops two key skills: the encoder gains the ability to comprehend the input context, while the decoder acquires the capability to generate coherent text.

Training Encoder-Decoder Models with a Denoising Autoencoding Objective

A research team is pre-training a language model with the specific goal of making it highly proficient at understanding long-range contextual relationships and the logical flow of arguments within a paragraph. They use a method where the model learns to restore an original, clean text from a deliberately corrupted version. Which of the following corruption strategies applied to the input text would be most effective for achieving the team's specific goal?

A developer is building a language model intended to automatically correct common typos and grammatical errors in user-generated text. They decide to use a pre-training method where the model learns to reconstruct an original, clean sentence from an artificially corrupted version of it. Propose two distinct types of corruption that should be introduced into the training data to best achieve the developer's goal. For each type of corruption, explain precisely how it would help the model learn to handle the intended errors.

Designing a Robust Text Correction Model

A language model is trained using a method where it must reconstruct an original, clean sentence from a version where 15% of the words have been randomly replaced with other words from the vocabulary. Analyze how this specific training process compels the model to develop a deeper understanding of sentence structure and word relationships, rather than simply memorizing the input sequence.

Analyzing the Impact of Input Corruption

In the context of denoising autoencoding for encoder-decoder models, span masking involves replacing one or more spans of tokens in an input sequence with mask symbols. For example, if the original sequence is corrupted into `[C] The kitten [M] is [M] .`, the model is trained to process this input and reconstruct the full, clean target sequence, generating `The kitten is chasing the ball .`.

Example of Span Masking in Denoising Autoencoding

Sentinel masking is a denoising autoencoding task where corrupted spans in the input are replaced by special sentinel tokens, such as `[X]` and `[Y]`. For instance, an input sequence might be corrupted to `[C] The kitten [X] the [Y]`. The encoder-decoder model is then trained to predict only the masked portions, outputting a sequence that reconstructs the missing tokens associated with each sentinel, such as `[X] is chasing [Y] ball .`.

Example of Sentinel Masking in Denoising Autoencoding

Denoising autoencoding is a pre-training approach, often used for encoder-decoder models, that trains a model to reconstruct an original, clean sequence from a corrupted input. The core task is to learn robust representations by removing the noise that was artificially introduced into the data.

Google

University of Michigan - Ann Arbor

Pre-training tasks are fundamental for developing universal language representations. After a model undergoes pre-training, various techniques are employed to adapt it for specific downstream applications. The pre-training tasks themselves are generally classified into three main types:

- **Supervised learning:** Training on data with explicit input-output pairs.
- **Unsupervised learning:** Discovering inherent knowledge from unlabeled data, such as through probabilistic language modeling.
- **Self-Supervised learning:** A hybrid approach where supervision signals are automatically generated from the data itself, as seen in masked language modeling (MLM).

Pre-training tasks

Qiu, X., Sun, T., Xu, Y., Shao, Y., Dai, N., & Huang, X. (2020). Pre-trained models for natural language processing: A survey. Science China Technological Sciences, 63(10), 1872-1897.

https://arxiv.org/abs/2003.08271. 

Pre-trained Models for Natural Language Processing: A Survey

Reference of Foundations of Large Language Models Course

It assumes some observed pairs of text that are more semantically similar than randomly sampled text.

There is a score function $s(x,y)$ for a text pair $(x,y)$ learned to minimize the objective function, where $(x, y^{+})$ are a similar pair and $y^{-}$ is presumably dissimilar to $x$.

Contrastive Learning (CTL)

There are several types of extensions of pre-trained models to better fit specific needs: Knowledge-Enriched PTMs, Multilingual and Language-Specific PTMs, Multi-Modal PTMs, Domain-Specific and Task-Specific PTMs, Model Compression, etc.

Extensions of PTMs

A fundamental issue following the pre-training phase is applying the generalized pre-trained model, denoted as $$g_{\hat{\theta}}(\cdot)$$, to specific downstream tasks. To successfully adapt the model to these downstream tasks, it is necessary to slightly adjust its parameters, denoted as $$\hat{\theta}$$, using labeled data, or alternatively, to prompt the model with task descriptions.

Applying and Adapting Pre-trained Models to Downstream Tasks

Unsupervised pre-training, a key focus in the early resurgence of deep learning, involves optimizing a neural network's parameters using a task-agnostic criterion. Instead of relying on task-specific labels, this method uses objectives like minimizing the input's reconstruction cross-entropy. It is typically used as a preparatory phase before a model undergoes supervised training.

Unsupervised Pre-training

Supervised pre-training is an approach where a neural network, such as a sequence model designed to encode inputs into representations, is initially trained on a supervised task. This is achieved by combining the core model with a classification layer to form a complete system. This system is then trained on a labeled dataset for a specific pre-training objective, like sentiment classification, before it is adapted for other downstream tasks.

Supervised Pre-training

Self-supervised learning is a pre-training method where a neural network is trained using supervision signals it generates from the data itself, rather than from human-provided labels. This is accomplished by constructing training tasks directly from unlabeled data, for example, by having the system create its own pseudo-labels. This approach facilitates large-scale training for deep neural networks, which has proven highly successful for developing models proficient in various understanding, writing, and reasoning tasks.

Self-Supervised Learning

Pre-training paradigms differ primarily in their data requirements, underlying assumptions, and adaptation methods. Unsupervised pre-training utilizes large-scale unlabeled data to create a good preliminary starting point, though it still requires considerable effort to further train the model with labeled data. Supervised pre-training relies on labeled datasets from the outset, operating on the assumption that different tasks are related, which allows a model trained on one task to be transferred to another via tuning. In contrast, self-supervised pre-training leverages large-scale unlabeled data to train a model that can be efficiently adapted to new tasks through methods like fine-tuning or prompting.

Comparison of Pre-training Paradigms

Categorizing pre-training tasks based purely on model architecture is suboptimal because a single training objective can be applied across varying architectures (e.g., masked language modeling works for both encoder-only and encoder-decoder setups). Therefore, a better approach is to classify these tasks based on their specific training objectives.

Rationale for Categorizing Pre-training Tasks by Objective

Denoising Autoencoding

Despite their differences, various pre-training tasks can be evaluated and compared against one another by utilizing a consistent framework and a standardized experimental setup.

Comparability of Pre-training Tasks

The effectiveness of pre-trained models stems from the general nature of their training tasks. By learning from broad objectives rather than task-specific ones, these models build versatile representations. This generalist foundation enables them to achieve strong performance across a wide variety of NLP problems, often to the point of outperforming systems that were previously developed with specialized, supervised training for individual tasks.

Generality of Pre-training Tasks and Performance

Once a model has undergone pre-training, various techniques are necessary to adapt it for specific downstream applications. The selection of an appropriate adaptation method is a key step in leveraging pre-trained models effectively.

Applying Pre-trained Models to Downstream Tasks

Given the following training scenario, identify which category of pre-training task is being used (Supervised, Unsupervised, or Self-Supervised) and justify your answer by explaining how the training data and labels are handled.

Identifying a Pre-training Strategy

The landscape of pre-training includes a vast and diverse array of tasks, making an exhaustive list impractical. For deeper and more comprehensive discussions on the variety of available pre-training tasks, specialized survey papers on the topic are a valuable resource.

Breadth of Pre-training Tasks

A research team is developing a new language model and is considering different pre-training approaches. Match each pre-training scenario below with the correct category of learning it represents.

A language model is being trained on a large corpus of text from the internet. The training process involves randomly hiding 15% of the words in each sentence and then tasking the model with predicting the original identity of these hidden words based on the surrounding context. Which category of pre-training task does this scenario best exemplify, and why?

A machine learning engineer is tasked with developing a language model but has access to different types of datasets. Compare and contrast the three main categories of pre-training tasks (supervised, unsupervised, and self-supervised) in terms of their data requirements and the nature of their supervision signals. For each category, provide a hypothetical example of a task and dataset that would be appropriate.

Comparing Pre-training Task Categories

Pre-training tasks can be compared based on their input-output transformations and their applicability to specific model architectures. Language modeling variants (such as Causal and Prefix LM) focus on sequential text generation and are typically applied to decoder-only and encoder-decoder models. Masked language modeling approaches (e.g., MASS-style, BERT-style) rely on reconstructing masked tokens and are compatible with both encoder-only and encoder-decoder architectures. Permuted language modeling and discriminative training methods (like Next Sentence Prediction, Sentence Comparison, and Token Classification) are specifically tailored for encoder-only models. Finally, denoising autoencoding encompasses tasks such as token reordering, token deletion, span masking, sentinel masking, sentence reordering, and document rotation, which train encoder-decoder models to reconstruct original text from corrupted inputs.

Learn Before

Related

Learn After