DeepAI AI Chat
Log In Sign Up

AMR Parsing as Graph Prediction with Latent Alignment

by   Chunchuan Lyu, et al.

Abstract meaning representations (AMRs) are broad-coverage sentence-level semantic representations. AMRs represent sentences as rooted labeled directed acyclic graphs. AMR parsing is challenging partly due to the lack of annotated alignments between nodes in the graphs and words in the corresponding sentences. We introduce a neural parser which treats alignments as latent variables within a joint probabilistic model of concepts, relations and alignments. As exact inference requires marginalizing over alignments and is infeasible, we use the variational auto-encoding framework and a continuous relaxation of the discrete alignments. We show that joint modeling is preferable to using a pipeline of align and parse. The parser achieves the best reported results on the standard benchmark (74.4


page 1

page 2

page 3

page 4


A Differentiable Relaxation of Graph Segmentation and Alignment for AMR Parsing

Abstract Meaning Representations (AMR) are a broad-coverage semantic for...

Generic Axiomatization of Families of Noncrossing Graphs in Dependency Parsing

We present a simple encoding for unlabeled noncrossing graphs and show h...

Automatic Accuracy Prediction for AMR Parsing

Abstract Meaning Representation (AMR) represents sentences as directed, ...

DocAMR: Multi-Sentence AMR Representation and Evaluation

Despite extensive research on parsing of English sentences into Abstract...

Automatic Inference of Minimalist Grammars using an SMT-Solver

We introduce (1) a novel parser for Minimalist Grammars (MG), encoded as...

Probabilistic, Structure-Aware Algorithms for Improved Variety, Accuracy, and Coverage of AMR Alignments

We present algorithms for aligning components of Abstract Meaning Repres...

Joint learning of ontology and semantic parser from text

Semantic parsing methods are used for capturing and representing semanti...