FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flow

Abstract

Most sequence-to-sequence (seq2seq) models are autoregressive; they generate each token by conditioning on previously generated tokens. In contrast, non-autoregressive seq2seq models generate all tokens in one pass, which leads to increased efficiency through parallel processing on hardware such as GPUs. However, directly modeling the joint distribution of all tokens simultaneously is challenging, and even with increasingly complex model structures accuracy lags significantly behind autoregressive models. In this paper, we propose a simple, efficient, and effective model for non-autoregressive sequence generation using latent variable models. Specifically, we turn to generative flow, an elegant technique to model complex distributions using neural networks, and design several layers of flow tailored for modeling the conditional density of sequential latent variables. We evaluate this model on three neural machine translation (NMT) benchmark datasets, achieving comparable performance with state-of-the-art non-autoregressive NMT models and almost constant decoding time w.r.t the sequence length.

Accepted by EMNLP 2019 (Long Paper)

References in corpus (10)

• Adam: A Method for Stochastic Optimization
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• On the Convergence of Adam and Beyond
• Variational Inference with Normalizing Flows
• Density estimation using Real NVP
• Insertion Transformer: Flexible Sequence Generation via Insertion Operations
• Mixture Models for Diverse Machine Translation: Tricks of the Trade
• Latent Normalizing Flows for Discrete Sequences
• Insertion-based Decoding with automatically Inferred Generation Order
• MaCow: Masked Convolutional Generative Flow

Cited by in corpus (10)

• Aligned Cross Entropy for Non-Autoregressive Machine Translation
• SoftFlow: Probabilistic Framework for Normalizing Flow on Manifolds
• A Generalized Framework of Sequence Generation with Application to Undirected Sequence Models
• Neural Language Generation: Formulation, Methods, and Evaluation
• Cascaded Text Generation with Markov Transformers
• Fully Non-autoregressive Neural Machine Translation: Tricks of the Trade
• Spike-Triggered Non-Autoregressive Transformer for End-to-End Speech Recognition
• POINTER: Constrained Progressive Text Generation via Insertion-based Generative Pre-training
• Improving Non-autoregressive Neural Machine Translation with Monolingual Data
• On the Discrepancy between Density Estimation and Sequence Generation