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 development and test sets.
Cite
CITATION STYLE
Pourdamghani, N., Gao, Y., Hermjakob, U., & Knight, K. (2014). Aligning english strings with abstract meaning representation graphs. In EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference (pp. 425–429). Association for Computational Linguistics (ACL). https://doi.org/10.3115/v1/d14-1048
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
