AMR Parsing using Stack-LSTMs

Miguel Ballesteros, Yaser Al-Onaizan

2017-07-24EMNLP 2017 9POSAMR Parsing

Abstract

We present a transition-based AMR parser that directly generates AMR parses from plain text. We use Stack-LSTMs to represent our parser state and make decisions greedily. In our experiments, we show that our parser achieves very competitive scores on English using only AMR training data. Adding additional information, such as POS tags and dependency trees, improves the results further.

Results

TaskDatasetMetricValueModel
Semantic ParsingLDC2014T12F1 Full63Transition-based parser-Stack-LSTM
Semantic ParsingLDC2014T12F1 Newswire68Transition-based parser-Stack-LSTM
AMR ParsingLDC2014T12F1 Full63Transition-based parser-Stack-LSTM
AMR ParsingLDC2014T12F1 Newswire68Transition-based parser-Stack-LSTM

Related Papers