An AMR Aligner Tuned by Transition-based Parser

EMNLP 2018  ·  Yijia Liu, Wanxiang Che, Bo Zheng, Bing Qin, Ting Liu ·

In this paper, we propose a new rich resource enhanced AMR aligner which produces multiple alignments and a new transition system for AMR parsing along with its oracle parser. Our aligner is further tuned by our oracle parser via picking the alignment that leads to the highest-scored achievable AMR graph. Experimental results show that our aligner outperforms the rule-based aligner in previous work by achieving higher alignment F1 score and consistently improving two open-sourced AMR parsers. Based on our aligner and transition system, we develop a transition-based AMR parser that parses a sentence into its AMR graph directly. An ensemble of our parsers with only words and POS tags as input leads to 68.4 Smatch F1 score.

PDF Abstract EMNLP 2018 PDF EMNLP 2018 Abstract


  Add Datasets introduced or used in this paper

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
AMR Parsing LDC2014T12 Transition-based+improved aligner+ensemble F1 Full 68.4 # 6
F1 Newswire 73.3 # 1
AMR Parsing LDC2014T12: Transition-based+improved aligner+ensemble F1 Newswire 0.73 # 2
F1 Full 0.68 # 2


No methods listed for this paper. Add relevant methods here