List your company
ResearchFormerly WizWand

AMR Parsing on LDC2014T12 (Full)

70F1 ScoreGoodman et al. (2016)
57.5260.766467.24Jul 24, 2017Oct 5, 2017Dec 18, 2017Mar 1, 2018May 14, 2018Jul 26, 2018Oct 8, 2018
Updated 8mo ago

Evaluation results

MethodLinks
Goodman et al. (2016)POS=true, DEP=true, NER=true, Pipeline System=true2017.0770
Transition-based AMR ParserInput features=Word + POS, Aligner=Our aligner, Ensemble size=102018.1068.4
Transition-based AMR ParserInput features=Word only, Aligner=Our aligner, Ensemble size=102018.1068.1
Wang and Xue2018.1068.1
Transition-based AMR ParserInput features=Word + POS, Aligner=Our aligner, Ensemble size=32018.1067.7
Transition-based AMR ParserInput features=Word only, Aligner=Our aligner, Ensemble size=32018.1067.4
Pust et al.2018.1067.1
Flanigan et al. (2016)POS=true, DEP=true, NER=true, Pipeline System=true2017.0766
Zhou et al. (2016)POS=true, DEP=true, NER=true, SRL=true, Pipeline System=true2017.0766
Pust et al. (2015)LM=true, NER=true, WordNet=true2017.0766
Wang et al. (2015a)POS=true, DEP=true, NER=true, SRL=true, Pipeline System=true2017.0766
Damonte et al.2018.1066
Wang et al.2018.1066
Zhou et al.2018.1066
Transition-based AMR ParserInput features=Word + POS, Aligner=Our aligner, Ensemble size=12018.1065.2
Transition-based AMR ParserInput features=Word only, Aligner=Our aligner, Ensemble size=12018.1064.7
Transition-based AMR ParserInput features=Word + POS, Aligner=JAMR aligner, Ensemble size=12018.1064.6
Damonte et al. (2016)POS=true, DEP=true, NER=true, SRL=true, Note=trained with LDC2014 training set2017.0764
Stack-LSTM AMR parserPre-trained word embeddings=true, Character-based representations=true, POS=true, DEP=true2017.0764
Ballesteros and Al-OnaizanInput features=Word + POS + DEP2018.1064
Transition-based AMR ParserInput features=Word only, Aligner=JAMR aligner, Ensemble size=12018.1063.9
Stack-LSTM AMR parserPre-trained word embeddings=true, Character-based representations=true2017.0763
Stack-LSTM AMR parserPre-trained word embeddings=true, Character-based representations=true, POS=true2017.0763
Ballesteros and Al-OnaizanInput features=Word only2018.1063
Ballesteros and Al-OnaizanInput features=Word + POS2018.1063
Stack-LSTM AMR parserPre-trained word embeddings=true, Character-based representations=false2017.0762
Damonte et al. (2016)POS=true, DEP=true, NER=true, SRL=true, Note=LDC2015 pretrained model evaluated on LDC20142017.0761
Pust et al. (2015)LM=true, NER=true2017.0761
Stack-LSTM AMR parserPre-trained word embeddings=false, Character-based representations=true2017.0761
Wang et al. (2015b)POS=true, DEP=true, NER=true, Pipeline System=true2017.0759
Stack-LSTM AMR parserPre-trained word embeddings=false, Character-based representations=false2017.0759
Flanigan et al. (2014)POS=true, DEP=true, Pipeline System=true2017.0758