Paper Info
Title
RIGA at SemEval-2016 Task 8: Impact of Smatch Extensions and Character-Level Neural Translation on AMR Parsing Accuracy.
Abstract
Two extensions to the AMR smatch scoring script are presented. The first extension com-bines the smatch scoring script with the C6.0 rule-based classifier to produce a human-readable report on the error patterns frequency observed in the scored AMR graphs. This first extension results in 4% gain over the state-of-art CAMR baseline parser by adding to it a manually crafted wrapper fixing the identified CAMR parser errors. The second extension combines a per-sentence smatch with an en-semble method for selecting the best AMR graph among the set of AMR graphs for the same sentence. This second modification au-tomatically yields further 0.4% gain when ap-plied to outputs of two nondeterministic AMR parsers: a CAMR+wrapper parser and a novel character-level neural translation AMR parser. For AMR parsing task the character-level neural translation attains surprising 7% gain over the carefully optimized word-level neural translation. Overall, we achieve smatch F1=62% on the SemEval-2016 official scor-ing set and F1=67% on the LDC2015E86 test set.
Year
DOI
Venue
2016
10.18653/v1/S16-1176
SemEval@NAACL-HLT
DocType
Volume
Citations 
Conference
abs/1604.01278
8
PageRank 
References 
Authors
0.57
10
2
Name
Order
Citations
PageRank
Guntis Barzdins112118.62
Didzis Gosko2173.62