Semantic Role Labeling of NomBank Partitives
This work addresses a specific linguistic annotation task for NLP researchers, but it is incremental as it applies existing methods to a narrow domain.
The paper tackled Semantic Role Labeling for English partitive nouns in the NomBank corpus, achieving an F1 score of 91.74% with gold parses and 91.12% with a neural parser.
This article is about Semantic Role Labeling for English partitive nouns (5%/REL of the price/ARG1; The price/ARG1 rose 5 percent/REL) in the NomBank annotated corpus. Several systems are described using traditional and transformer-based machine learning, as well as ensembling. Our highest scoring system achieves an F1 of 91.74% using "gold" parses from the Penn Treebank and 91.12% when using the Berkeley Neural parser. This research includes both classroom and experimental settings for system development.