An Incremental Parser for Abstract Meaning Representation

Marco Damonte, Shay B. Cohen, Giorgio Satta
8/22/2016
cs.CL

Official code: mdtux89/amr-evaluation (29 stars, last commit 2020-02-10).

Abstract

Meaning Representation (AMR) is a semantic representation for natural language that embeds annotations related to traditional tasks such as named entity recognition, semantic role labeling, word sense disambiguation and co-reference resolution. We describe a transition-based parser for AMR that parses sentences left-to-right, in linear time. We further propose a test-suite that assesses specific subtasks that are helpful in comparing AMR parsers, and show that our parser is competitive with the state of the art on the LDC2015E86 dataset and that it outperforms state-of-the-art parsers for recovering named entities and handling polarity.

View on arXivView PDF

Code Implementations(1)

mdtux89/amr-evaluationOfficial100%

Evaluation metrics to compare AMR graphs based on Smatch

297Shell, PythonOct 6, 20166 years ago

Similar Papers

TRANX: A Transition-based Neural Abstract Syntax Parser for Semantic Parsing and Code Generation

84% match1 repo4642018

Evaluating Scoped Meaning Representations

83% match1 repo202018

A Pilot Study for Chinese SQL Semantic Parsing

82% match1 repo2072019

Widely Interpretable Semantic Representation: Frameless Meaning Representation for Broader Applicability

81% match2023

A Probabilistic Generative Grammar for Semantic Parsing

80% match2 repos302016

Correcting Semantic Parses with Natural Language through Dynamic Schema Encoding

80% match1 repo32023

Cite this paper

@article{damonte2016incremental,
  title  = {An Incremental Parser for Abstract Meaning Representation},
  author = {Marco Damonte and Shay B. Cohen and Giorgio Satta},
  year   = {2016},
  eprint = {1608.06111},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1608.06111}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1608.06111.svg)](https://codeofpaper.com/paper/1608.06111)

Discussion