no code implementations • ACL 2022 • Lisa Jin, Daniel Gildea
A common way to combat exposure bias is by applying scores from evaluation metrics as rewards in reinforcement learning (RL).
1 code implementation • 22 Jun 2022 • Lisa Jin, Linfeng Song, Lifeng Jin, Dong Yu, Daniel Gildea
HCT (i) tags the source string with token-level edit actions and slotted rules and (ii) fills in the resulting rule slots with spans from the dialogue context.
no code implementations • 27 Aug 2021 • Lisa Jin, Daniel Gildea
Graph encoders in AMR-to-text generation models often rely on neighborhood convolutions or global vertex attention.
no code implementations • 27 Aug 2021 • Lisa Jin, Daniel Gildea
Text generation from AMR requires mapping a semantic graph to a string that it annotates.
no code implementations • COLING 2020 • Lisa Jin, Daniel Gildea
Instead of feeding shortest paths to the vertex self-attention module, we train a model to learn them using generalized shortest-paths algorithms.
no code implementations • 3 Dec 2019 • Lisa Jin, Daniel Gildea
To enforce a sentence-aligned graph traversal and provide local graph context, we predict transition-based parser actions in addition to English words.