Promises and Pitfalls of Generative Masked Language Modeling: Theoretical Framework and Practical Guidelines

• URL: http://arxiv.org/abs/2407.21046v1
• Date: Mon, 22 Jul 2024 18:00:00 GMT
• Title: Promises and Pitfalls of Generative Masked Language Modeling: Theoretical Framework and Practical Guidelines
• Authors: Yuchen Li, Alexandre Kirchmeyer, Aashay Mehta, Yilong Qin, Boris Dadachev, Kishore Papineni, Sanjiv Kumar, Andrej Risteski,
• Abstract summary: We focus on Generative Masked Language Models (GMLMs) We train a model to fit conditional probabilities of the data distribution via masking, which are subsequently used as inputs to a Markov Chain to draw samples from the model. We adapt the T5 model for iteratively-refined parallel decoding, achieving 2-3x speedup in machine translation with minimal sacrifice in quality.
• Score: 74.42485647685272
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Autoregressive language models are the currently dominant paradigm for text generation, but they have some fundamental limitations that cannot be remedied by scale-for example inherently sequential and unidirectional generation. While alternate classes of models have been explored, we have limited mathematical understanding of their fundamental power and limitations. In this paper we focus on Generative Masked Language Models (GMLMs), a non-autoregressive paradigm in which we train a model to fit conditional probabilities of the data distribution via masking, which are subsequently used as inputs to a Markov Chain to draw samples from the model, These models empirically strike a promising speed-quality trade-off as each step can be typically parallelized by decoding the entire sequence in parallel. We develop a mathematical framework for analyzing and improving such models which sheds light on questions of sample complexity and inference speed and quality. Empirically, we adapt the T5 model for iteratively-refined parallel decoding, achieving 2-3x speedup in machine translation with minimal sacrifice in quality compared with autoregressive models. We run careful ablation experiments to give recommendations on key design choices, and make fine-grained observations on the common error modes in connection with our theory. Our mathematical analyses and empirical observations characterize both potentials and limitations of this approach, and can be applied to future works on improving understanding and performance of GMLMs. Our codes are released at https://github.com/google-research/google-research/tree/master/padir

Related papers

• Model Stealing for Any Low-Rank Language Model [25.16701867917684]
  We build a theoretical understanding of stealing language models by studying a simple and mathematically tractable setting. Our main result is an efficient algorithm in the conditional query model, for learning any low-rank distribution. This is an interesting example where, at least theoretically, allowing a machine learning model to solve more complex problems at inference time can lead to drastic improvements in its performance.
  arXiv  Detail & Related papers  (2024-11-12T04:25:31Z)
• Meaning Representations from Trajectories in Autoregressive Models [106.63181745054571]
  We propose to extract meaning representations from autoregressive language models by considering the distribution of all possible trajectories extending an input text. This strategy is prompt-free, does not require fine-tuning, and is applicable to any pre-trained autoregressive model. We empirically show that the representations obtained from large models align well with human annotations, outperform other zero-shot and prompt-free methods on semantic similarity tasks, and can be used to solve more complex entailment and containment tasks that standard embeddings cannot handle.
  arXiv  Detail & Related papers  (2023-10-23T04:35:58Z)
• SequenceMatch: Imitation Learning for Autoregressive Sequence Modelling with Backtracking [60.109453252858806]
  A maximum-likelihood (MLE) objective does not match a downstream use-case of autoregressively generating high-quality sequences. We formulate sequence generation as an imitation learning (IL) problem. This allows us to minimize a variety of divergences between the distribution of sequences generated by an autoregressive model and sequences from a dataset. Our resulting method, SequenceMatch, can be implemented without adversarial training or architectural changes.
  arXiv  Detail & Related papers  (2023-06-08T17:59:58Z)
• Twist Decoding: Diverse Generators Guide Each Other [116.20780037268801]
  We introduce Twist decoding, a simple and general inference algorithm that generates text while benefiting from diverse models. Our method does not assume the vocabulary, tokenization or even generation order is shared.
  arXiv  Detail & Related papers  (2022-05-19T01:27:53Z)
• Model-based micro-data reinforcement learning: what are the crucial model properties and which model to choose? [0.2836066255205732]
  We contribute to micro-data model-based reinforcement learning (MBRL) by rigorously comparing popular generative models. We find that on an environment that requires multimodal posterior predictives, mixture density nets outperform all other models by a large margin. We also found that deterministic models are on par, in fact they consistently (although non-significantly) outperform their probabilistic counterparts.
  arXiv  Detail & Related papers  (2021-07-24T11:38:25Z)
• BODAME: Bilevel Optimization for Defense Against Model Extraction [10.877450596327407]
  We consider an adversarial setting to prevent model extraction under the assumption that will make best guess on the service provider's attacker. We formulate a surrogate model using the predictions of the true model. We give a tractable transformation and an algorithm for more complicated models that are learned by using gradient descent-based algorithms.
  arXiv  Detail & Related papers  (2021-03-11T17:08:31Z)
• Aligned Cross Entropy for Non-Autoregressive Machine Translation [120.15069387374717]
  We propose aligned cross entropy (AXE) as an alternative loss function for training of non-autoregressive models. AXE-based training of conditional masked language models (CMLMs) substantially improves performance on major WMT benchmarks.
  arXiv  Detail & Related papers  (2020-04-03T16:24:47Z)
• AvgOut: A Simple Output-Probability Measure to Eliminate Dull Responses [97.50616524350123]
  We build dialogue models that are dynamically aware of what utterances or tokens are dull without any feature-engineering. The first model, MinAvgOut, directly maximizes the diversity score through the output distributions of each batch. The second model, Label Fine-Tuning (LFT), prepends to the source sequence a label continuously scaled by the diversity score to control the diversity level. The third model, RL, adopts Reinforcement Learning and treats the diversity score as a reward signal.
  arXiv  Detail & Related papers  (2020-01-15T18:32:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.