UC Davis at SemEval-2019 Task 1: DAG Semantic Parsing with Attention-based Decoder

Dian Yu, Kenji Sagae

Abstract

We present an encoder-decoder model for semantic parsing with UCCA SemEval 2019 Task 1. The encoder is a Bi-LSTM and the decoder uses recursive self-attention. The proposed model alleviates challenges and feature engineering in traditional transition-based and graph-based parsers. The resulting parser is simple and proved to effective on the semantic parsing task.
BibTeX
@inproceedings{yu2019uc,
  author = {Dian Yu and Kenji Sagae},
  title = {{UC Davis at SemEval-2019 Task 1: DAG Semantic Parsing with Attention-based Decoder}},
  booktitle = {SemEval @ NAACL},
  year = {2019},
  doi = {10.18653/v1/s19-2017},
}

Loading related content...

Figure