Skip to content
conftrace_
2019 NAACL NAACL 2019

BERT has a Mouth, and It Must Speak: BERT as a Markov Random Field Language Model

AbstractWe show that BERT (Devlin et al., 2018) is a Markov random field language model. This formulation gives way to a natural procedure to sample sentences from BERT. We generate from BERT and find that it can produce high quality, fluent generations. Compared to the generations of a traditional left-to-right language model, BERT generates sentences that are more diverse but of slightly worse quality.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing

More from NAACL 2019

All NAACL 2019 papers →