Conference paper
Inducing and Using Alignments for Transition-based AMR Parsing
Andrew Drozdov, Jiawei Zhou, et al.
NAACL 2022
Our work involves enriching the Stack-LSTM transition-based AMR parser (Ballesteros and Al-Onaizan, 2017) by augmenting training with Policy Learning and rewarding the Smatch score of sampled graphs. In addition, we also combined several AMR-to-text alignments with an attention mechanism and we supplemented the parser with pre-processed concept identification, named entities and contextualized embeddings. We achieve a highly competitive performance that is comparable to the best published results. We show an in-depth study ablating each of the new components of the parser.
Andrew Drozdov, Jiawei Zhou, et al.
NAACL 2022
Guanhua Zhang, Bing Bai, et al.
ACL 2019
Yufang Hou, Charles Jochim, et al.
ACL 2019
Roy Bar-Haim, Dalia Krieger, et al.
ACL 2019