论文标题
GAMMT：使用多个变压器的生成歧义建模
GAMMT: Generative Ambiguity Modeling Using Multiple Transformers
论文作者
论文摘要
我们介绍了一个名为GAMMT（使用多个变压器的生成歧义模型）的新型模型，以基于概率集的顺序数据。与常规模型不同，我们的方法承认，序列的数据生成过程不是确定性的，而是模棱两可的，并且受一组概率的影响。为了捕捉这种歧义，伽玛特采用了多个通过选择机制链接的平行变压器，从而允许模棱两可的概率近似。我们方法的生成性质还可以实现输入令牌和序列的多种表示。尽管我们的模型尚未经过实验验证，但我们认为，我们的模型具有实现不确定数据生成过程的建模序列中高质量和多样性的巨大潜力。
We introduce a novel model called GAMMT (Generative Ambiguity Models using Multiple Transformers) for sequential data that is based on sets of probabilities. Unlike conventional models, our approach acknowledges that the data generation process of a sequence is not deterministic, but rather ambiguous and influenced by a set of probabilities. To capture this ambiguity, GAMMT employs multiple parallel transformers that are linked by a selection mechanism, allowing for the approximation of ambiguous probabilities. The generative nature of our approach also enables multiple representations of input tokens and sequences. While our models have not yet undergone experimental validation, we believe that our model has great potential to achieve high quality and diversity in modeling sequences with uncertain data generation processes.
