Yangtian Zhang
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper introduces the Insertion Process (IP), a novel stochastic generative model that learns variable-length, non-monotonic sequence generation by explicitly modeling the insertion order of tokens.
The paper introduces the Insertion Process (IP), a novel stochastic generative model that learns variable-length, non-monotonic sequence generation by explicitly modeling the insertion order of tokens.
Papers
Variational Learning for Insertion-based Generation
Yangtian Zhang, Zhe Wang, Arthur Gretton, Rex Ying +3 more
The paper introduces the Insertion Process (IP), a novel stochastic generative model that learns variable-length, non-monotonic sequence generation by explicitly modeling the insertion order of tokens…