arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1806.04550cs.LGcs.CLstat.ML
收藏

无条件词生成的深层状态空间模型

Deep State Space Models for Unconditional Word Generation

ETH Zürich(苏黎世联邦理工学院)

Florian Schmidt, Thomas Hofmann

摘要:

自回归反馈被认为是成功的无条件文本生成使用随机序列模型的必要条件。然而,这种反馈会在训练过程中引入系统性偏差,并且模糊了生成的原则:致力于全局信息,忘记局部细微差别。我们表明,一个非自回归深状态空间模型具有明确的分离的全球和局部的不确定性,可以建立从只有两个成分:一个独立的噪声源和一个确定性的过渡函数。基于流的变分推理的最新进展可以用来训练证据下界,而不诉诸退火,辅助损失或类似的措施。其结果是一个高度可解释的生成模型与可比的自回归模型的任务的单词生成。

英文摘要:

Autoregressive feedback is considered a necessity for successful unconditional text generation using stochastic sequence models. However, such feedback is known to introduce systematic biases into the training process and it obscures a principle of generation: committing to global information and forgetting local nuances. We show that a non-autoregressive deep state space model with a clear separation of global and local uncertainty can be built from only two ingredients: An independent noise source and a deterministic transition function. Recent advances on flow-based variational inference can be used to train an evidence lower-bound without resorting to annealing, auxiliary losses or similar measures. The result is a highly interpretable generative model on par with comparable auto-regressive models on the task of word generation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑