LaMer. Implementation of "Non-Parallel Text Style Transfer with Self-Parallel Supervision" (ICLR 2022) — mines roughly parallel sentences from non-parallel data via scene graphs, trains BART with MLE, and refines with contrastive imitation learning.

Problem

The full read on this project is a sign-in away — what it solves, who it serves, and where it sits in the market.

Audience

The full read on this project is a sign-in away — what it solves, who it serves, and where it sits in the market.

Market

The full read on this project is a sign-in away — what it solves, who it serves, and where it sits in the market.

Pricing

The full read on this project is a sign-in away — what it solves, who it serves, and where it sits in the market.