AMR-to-Text Generation with Cache Transition Systems
This work addresses text generation from structured semantic representations for natural language processing applications, presenting an incremental improvement over existing neural methods.
The paper tackles the problem of generating text from Abstract Meaning Representation (AMR) graphs by directly encoding graph structure and using transition-based parser actions to guide traversal, achieving competitive performance on standard benchmarks.
Text generation from AMR involves emitting sentences that reflect the meaning of their AMR annotations. Neural sequence-to-sequence models have successfully been used to decode strings from flattened graphs (e.g., using depth-first or random traversal). Such models often rely on attention-based decoders to map AMR node to English token sequences. Instead of linearizing AMR, we directly encode its graph structure and delegate traversal to the decoder. To enforce a sentence-aligned graph traversal and provide local graph context, we predict transition-based parser actions in addition to English words. We present two model variants: one generates parser actions prior to words, while the other interleaves actions with words.