List your company
ResearchFormerly WizWand

AMR parsing on LDC2014T12 Newswire section

73.3F1 ScoreTransition-based AMR Parser
58.42862.28966.1570.011Jul 24, 2017Oct 5, 2017Dec 18, 2017Mar 1, 2018May 14, 2018Jul 26, 2018Oct 8, 2018
Updated 8mo ago

Evaluation results

MethodLinks
Transition-based AMR ParserInput features=Word + POS, Aligner=Our aligner, Ensemble size=102018.1073.3
Transition-based AMR ParserInput features=Word only, Aligner=Our aligner, Ensemble size=102018.1072.5
Transition-based AMR ParserInput features=Word + POS, Aligner=Our aligner, Ensemble size=32018.1072.5
Transition-based AMR ParserInput features=Word only, Aligner=Our aligner, Ensemble size=32018.1071.9
Zhou et al. (2016)POS=true, DEP=true, NER=true, SRL=true, Pipeline System=true2017.0771
Zhou et al.2018.1071
Wang et al. (2015a)POS=true, DEP=true, NER=true, SRL=true, Pipeline System=true2017.0770
Wang et al.2018.1070
Goodman et al.2018.1070
Transition-based AMR ParserInput features=Word + POS, Aligner=Our aligner, Ensemble size=12018.1069.8
Transition-based AMR ParserInput features=Word only, Aligner=Our aligner, Ensemble size=12018.1069.3
Stack-LSTM AMR parserPre-trained word embeddings=true, Character-based representations=true, POS=true, DEP=true2017.0769
Ballesteros and Al-OnaizanInput features=Word + POS + DEP2018.1069
Transition-based AMR ParserInput features=Word + POS, Aligner=JAMR aligner, Ensemble size=12018.1068.8
Transition-based AMR ParserInput features=Word only, Aligner=JAMR aligner, Ensemble size=12018.1068.6
Stack-LSTM AMR parserPre-trained word embeddings=true, Character-based representations=true2017.0768
Stack-LSTM AMR parserPre-trained word embeddings=true, Character-based representations=true, POS=true2017.0768
Ballesteros and Al-OnaizanInput features=Word only2018.1068
Ballesteros and Al-OnaizanInput features=Word + POS2018.1068
Artzi et al.2018.1066.3
Artzi et al. (2015)POS=true, CCG=true2017.0766
Stack-LSTM AMR parserPre-trained word embeddings=false, Character-based representations=true2017.0766
Stack-LSTM AMR parserPre-trained word embeddings=true, Character-based representations=false2017.0766
Stack-LSTM AMR parserPre-trained word embeddings=false, Character-based representations=false2017.0764
Wang et al. (2015b)POS=true, DEP=true, NER=true, Pipeline System=true2017.0763
Werling et al. (2015)POS=true, DEP=true, NER=true, Pipeline System=true2017.0762
Flanigan et al. (2014)POS=true, DEP=true, Pipeline System=true2017.0759