all AI news
Graph Pre-training for AMR Parsing and Generation. (arXiv:2203.07836v4 [cs.CL] UPDATED)
May 5, 2022, 1:11 a.m. | Xuefeng Bai, Yulong Chen, Yue Zhang
cs.CL updates on arXiv.org arxiv.org
Abstract meaning representation (AMR) highlights the core semantic
information of text in a graph structure. Recently, pre-trained language models
(PLMs) have advanced tasks of AMR parsing and AMR-to-text generation,
respectively. However, PLMs are typically pre-trained on textual data, thus are
sub-optimal for modeling structural knowledge. To this end, we investigate
graph self-supervised training to improve the structure awareness of PLMs over
AMR graphs. In particular, we introduce two graph auto-encoding strategies for
graph-to-graph pre-training and four tasks to integrate text …
More from arxiv.org / cs.CL updates on arXiv.org
Jobs in AI, ML, Big Data
Software Engineer for AI Training Data (School Specific)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Python)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Tier 2)
@ G2i Inc | Remote
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US