research product . program source code . 2019

AMR parse quality prediction [Source Code]

Opitz, Juri (Department of Computational Linguistics, Heidelberg University, Germany);
  • Published: 01 Jan 2019
  • Publisher: heiDATA
Abstract
<p>Accuracy prediction for AMR parsing predicts 33 accuracy metrics for a given sentence and its (automatic) AMR parse</p> <p><strong>Abstract (Opitz and Frank, 2019):</strong></p> <p>Semantic proto-role labeling (SPRL) is an alternative to semantic role labeling (SRL) that moves beyond a categorical definition of roles, following Dowty's feature-based view of proto-roles. This theory determines agenthood vs. patienthood based on a participant's instantiation of more or less typical agent vs. patient properties, such as, for example, volition in an event. To perform SPRL, we develop an ensemble of hierarchical models with self-attention and concurrently learned ...
Subjects
free text keywords: Abstract Meaning Representation AMR, Arts and Humanities, Computer and Information Science, NLP, knowledge graph, semantic parsing, textual semantic analysis, Humanities
Communities
Digital Humanities and Cultural Heritage
Download from
B2FIND
program source code . 2019
Provider: B2FIND
Any information missing or wrong?Report an Issue