AMR Parsing on LDC2014T12 (Full)
70F1 ScoreGoodman et al. (2016)
Evaluation Results
| Method | Links | |
|---|---|---|
| Goodman et al. (2016)POS=true, DEP=true, NER=true, Pipeline System=true2017.07 | 70 | |
| Transition-based AMR ParserInput features=Word + POS, Aligner=Our aligner, Ensemble size=102018.10 | 68.4 | |
| Transition-based AMR ParserInput features=Word only, Aligner=Our aligner, Ensemble size=102018.10 | 68.1 | |
| Wang and Xue2018.10 | 68.1 | |
| Transition-based AMR ParserInput features=Word + POS, Aligner=Our aligner, Ensemble size=32018.10 | 67.7 | |
| Transition-based AMR ParserInput features=Word only, Aligner=Our aligner, Ensemble size=32018.10 | 67.4 | |
| Pust et al.2018.10 | 67.1 | |
| Flanigan et al. (2016)POS=true, DEP=true, NER=true, Pipeline System=true2017.07 | 66 | |
| Zhou et al. (2016)POS=true, DEP=true, NER=true, SRL=true, Pipeline System=true2017.07 | 66 | |
| Pust et al. (2015)LM=true, NER=true, WordNet=true2017.07 | 66 | |
| Wang et al. (2015a)POS=true, DEP=true, NER=true, SRL=true, Pipeline System=true2017.07 | 66 | |
| Damonte et al.2018.10 | 66 | |
| Wang et al.2018.10 | 66 | |
| Zhou et al.2018.10 | 66 | |
| Transition-based AMR ParserInput features=Word + POS, Aligner=Our aligner, Ensemble size=12018.10 | 65.2 | |
| Transition-based AMR ParserInput features=Word only, Aligner=Our aligner, Ensemble size=12018.10 | 64.7 | |
| Transition-based AMR ParserInput features=Word + POS, Aligner=JAMR aligner, Ensemble size=12018.10 | 64.6 | |
| Damonte et al. (2016)POS=true, DEP=true, NER=true, SRL=true, Note=trained with LDC2014 training set2017.07 | 64 | |
| Stack-LSTM AMR parserPre-trained word embeddings=true, Character-based representations=true, POS=true, DEP=true2017.07 | 64 | |
| Ballesteros and Al-OnaizanInput features=Word + POS + DEP2018.10 | 64 | |
| Transition-based AMR ParserInput features=Word only, Aligner=JAMR aligner, Ensemble size=12018.10 | 63.9 | |
| Stack-LSTM AMR parserPre-trained word embeddings=true, Character-based representations=true2017.07 | 63 | |
| Stack-LSTM AMR parserPre-trained word embeddings=true, Character-based representations=true, POS=true2017.07 | 63 | |
| Ballesteros and Al-OnaizanInput features=Word only2018.10 | 63 | |
| Ballesteros and Al-OnaizanInput features=Word + POS2018.10 | 63 | |
| Stack-LSTM AMR parserPre-trained word embeddings=true, Character-based representations=false2017.07 | 62 | |
| Damonte et al. (2016)POS=true, DEP=true, NER=true, SRL=true, Note=LDC2015 pretrained model evaluated on LDC20142017.07 | 61 | |
| Pust et al. (2015)LM=true, NER=true2017.07 | 61 | |
| Stack-LSTM AMR parserPre-trained word embeddings=false, Character-based representations=true2017.07 | 61 | |
| Wang et al. (2015b)POS=true, DEP=true, NER=true, Pipeline System=true2017.07 | 59 | |
| Stack-LSTM AMR parserPre-trained word embeddings=false, Character-based representations=false2017.07 | 59 | |
| Flanigan et al. (2014)POS=true, DEP=true, Pipeline System=true2017.07 | 58 |