SEQ2SEQ + 20M

Reported on 2 benchmarks across 2 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing2 results

Semantic ParsingonLDC2015E86
Smatch· 2017-04-26
62.1
best: 73.7 (Joint model)
Neural AMR: Sequence-to-Sequence Models for Parsing and Generation arXiv:1704.08381
AMR ParsingonLDC2015E86
Smatch· 2017-04-26
62.1
best: 73.7 (Joint model)
Neural AMR: Sequence-to-Sequence Models for Parsing and Generation arXiv:1704.08381