Aligning English Strings with Abstract Meaning Representation Graphs

Abstract

We align pairs of English sentences and corresponding Abstract Meaning Representations (AMR), at the token level. Such alignments will be useful for downstream extraction of semantic interpretation and generation rules. Our method involves linearizing AMR structures and performing symmetrized EM training. We obtain 86.5% and 83.1% alignment F score on… (More)

Topics

3 Figures and Tables

Statistics

050100201520162017
Citations per Year

Citation Velocity: 37

Averaging 37 citations per year over the last 3 years.

Learn more about how we calculate this metric in our FAQ.

Slides referencing similar topics