AMR Parsing using Stack-LSTMs

TL;DR

This paper introduces a transition-based AMR parser utilizing Stack-LSTMs that directly converts plain text into AMR graphs, achieving competitive results with potential improvements from auxiliary linguistic features.

Contribution

It presents a novel Stack-LSTM-based transition parser for AMR that operates directly from text and demonstrates competitive performance with simple and extended features.

Findings

Achieves competitive AMR parsing scores on English.

Adding POS tags and dependency trees improves accuracy.

Uses greedy decision-making with Stack-LSTMs for 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.