N
Nathan Schneider
Researcher at Georgetown University
Publications - 131
Citations - 5825
Nathan Schneider is an academic researcher from Georgetown University. The author has contributed to research in topics: Parsing & Annotation. The author has an hindex of 25, co-authored 130 publications receiving 5138 citations. Previous affiliations of Nathan Schneider include University of Washington & Carnegie Mellon University.
Papers
More filters
Posted Content
A Corpus of Adpositional Supersenses for Mandarin Chinese
TL;DR: This paper presents a corpus in which all adpositions have been semantically annotated in Mandarin Chinese; to the best of the knowledge, this is the first Chinese corpus to be broadly annotated with adposition semantics.
Adpositional Supersenses for Mandarin Chinese
TL;DR: This study adapts Semantic Network of Adposition and Case Supersenses (SNACS) annotation to Mandarin Chinese and demonstrates that the same supersense categories are appropriate for Chinese adposition semantics.
Posted Content
Supertagging the Long Tail with Tree-Structured Decoding of Complex Categories
TL;DR: This best tagger is capable of recovering a sizeable fraction of the long-tail supertags and even generates CCG categories that have never been seen in training, while approximating the prior state of the art in overall tag accuracy with fewer parameters.
Posted Content
Semantically Constrained Multilayer Annotation: The Case of Coreference
TL;DR: A coreference annotation scheme is proposed as a layer on top of the Universal Conceptual Cognitive Annotation foundational layer, treating units in predicate-argument structure as a basis for entity and event mentions, arguing that this allows coreference annotators to sidestep some of the challenges faced in other schemes.
Proceedings Article
A Corpus of Adpositional Supersenses for Mandarin Chinese.
TL;DR: The authors presented a corpus in which all adpositions have been semantically annotated in Mandarin Chinese; to the best of their knowledge, this is the first Chinese corpus to be broadly annotated with adposition semantics.