Data-to-text Generation by Splicing Together Nearest Neighbors
Sam Wisemana b c, Artūrs Bačkursa b c, Karl Stratosa b c
- aDuke University
- bMicrosoft Research
- cRutgers University
Papers open inside SciRah from the original publisher or repository; SciRah never hosts them.
Abstract
We propose to tackle data-to-text generation tasks by directly splicing together retrieved segments of text from "neighbor" sourcetarget pairs.Unlike recent work that conditions on retrieved neighbors but generates text token-by-token, left-to-right, we learn a policy that directly manipulates segments of neighbor text, by inserting or replacing them in partially constructed generations.Standard techniques for training such a policy require an oracle derivation for each generation, and we prove that finding the shortest such derivation can be reduced to parsing under a particular weighted context-free grammar.We find that policies learned in this way perform on par with strong baselines in terms of automatic and human evaluation, but allow for more interpretable and controllable generation.
TL;DRThis work learns a policy that directly manipulates segments of neighbor text, by inserting or replacing them in partially constructed generations, to tackle data-to-text generation tasks by directly splicing together retrieved segments of text from “neighbor” source-target pairs. (Semantic Scholar)