KERMIT: Generative Insertion-Based Modeling for Sequences

4 Jun 2019William ChanNikita KitaevKelvin GuuMitchell SternJakob Uszkoreit

We present KERMIT, a simple insertion-based approach to generative modeling for sequences and sequence pairs. KERMIT models the joint distribution and its decompositions (i.e., marginals and conditionals) using a single neural network and, unlike much prior work, does not rely on a prespecified factorization of the data distribution... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Machine Translation WMT2014 English-German KERMIT BLEU score 28.7 # 16