EventRR builds a Referential Event Graph from AMR parsing of the referring expression and uses graph-guided temporal reasoning over detector queries to select and segment the referent, reporting state-of-the-art results on four RVOS benchmarks.
Inducing and Using Alignments for Transition-based AMR Parsing
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Transition-based parsers for Abstract Meaning Representation (AMR) rely on node-to-word alignments. These alignments are learned separately from parser training and require a complex pipeline of rule-based components, pre-processing, and post-processing to satisfy domain-specific constraints. Parsers also train on a point-estimate of the alignment pipeline, neglecting the uncertainty due to the inherent ambiguity of alignment. In this work we explore two avenues for overcoming these limitations. First, we propose a neural aligner for AMR that learns node-to-word alignments without relying on complex pipelines. We subsequently explore a tighter integration of aligner and parser training by considering a distribution over oracle action sequences arising from aligner uncertainty. Empirical results show this approach leads to more accurate alignments and generalization better from the AMR2.0 to AMR3.0 corpora. We attain a new state-of-the art for gold-only trained models, matching silver-trained performance without the need for beam search on AMR3.0.
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
EventRR: Event Referential Reasoning for Referring Video Object Segmentation
EventRR builds a Referential Event Graph from AMR parsing of the referring expression and uses graph-guided temporal reasoning over detector queries to select and segment the referent, reporting state-of-the-art results on four RVOS benchmarks.