Aligning English Strings with Abstract Meaning Representation Graphs

We align pairs of English sentences and corresponding Abstract Meaning Representations (AMR), at the token level. Such alignments will be useful for downstream extraction of semantic interpretation and generation rules. Our method involves linearizing AMR structures and performing symmetrized EM training. We obtain 86.5% and 83.1% alignment F score on development and test sets.

Computer Science Linguistics

View graph Source

Paper

Full text

Aligning English Strings with Abstract Meaning Representation Graphs

Semantic Scholar · Computer Science · 2014

Abstract

We align pairs of English sentences and corresponding Abstract Meaning Representations (AMR), at the token level. Such alignments will be useful for downstream extraction of semantic interpretation and generation rules. Our method involves linearizing AMR structures and performing symmetrized EM training. We obtain 86.5% and 83.1% alignment F score on development and test sets.

Source of record · Semantic Scholar

Similar papers

A Structured Syntax-Semantics Interface for English-AMR AlignmentIda Szubert, Adam Lopez, Nathan Schneider2018 · North American Chapter of the Association for Computational Linguistics · 13 citations In Library

Probabilistic, Structure-Aware Algorithms for Improved Variety, Accuracy, and Coverage of AMR AlignmentsAustin Blodgett, Nathan Schneider2021 · arXiv (Cornell University) · 24 citations In Library

Align-smatch: A Novel Evaluation Method for Chinese Abstract Meaning Representation Parsing based on Alignment of Concept and RelationLiming Xiao, Bin Li, Zhixing Xu et al.2022 · International Conference on Language Resources and Evaluation · 3 citations In Library

Semantically Inspired AMR Alignment for the Portuguese LanguageRafael T. Anchiêta, Thiago Alexandre Salgueiro Pardo2020 · Conference on Empirical Methods in Natural Language Processing · 13 citations In Library

Cross-lingual AMR Aligner: Paying Attention to Cross-AttentionAbelardo Carlos Martínez Lorenzo, ‪Pere-Lluís Huguet Cabot, Roberto Navigli2022 · arXiv (Cornell University) · 6 citations In Library

Cross-lingual AMR Aligner: Paying Attention to Cross-AttentionAbelardo Carlos Martínez Lorenzo, Pere Lluís Huguet Cabot, Roberto Navigli2023 In Library

AMR Parsing as Graph Prediction with Latent AlignmentChunchuan Lyu, Ivan Titov2018 · Annual Meeting of the Association for Computational Linguistics · 134 citations In Library

Cross-lingual Abstract Meaning Representation ParsingMarco Damonte, Shay B. Cohen2017 · North American Chapter of the Association for Computational Linguistics · 76 citations In Library

AMR Alignment for Morphologically-rich and Pro-drop LanguagesK. Elif Oral, Gülşen Eryiğit2022 · Annual Meeting of the Association for Computational Linguistics · 2 citations In Library

Using Syntax-Based Machine Translation to Parse English into Abstract Meaning RepresentationM. Pust, U. Hermjakob, Kevin Knight et al.2015 · arXiv.org · 17 citations In Library

Source of record

Semantic Scholar

44B

Welcome.

This panel sticks with you. Pick anything below and it opens right beside it, so you can dig through 60,000-plus records without ever losing your spot here.

Travel 44B

LibraryPapers, policy, standards, statute LabsEvery organization building AI ModelsIntelligence, price, and speed BenchmarksThe evaluation catalog IncidentsAI failures and harms SearchOne field across everything DashboardThe state of AI accountability in NY 44B RegistryThe Art. 44-B compliance portal