• Publications
  • Influence
A Corpus of Literal and Idiomatic Uses of German Infinitive-Verb Compounds
TLDR
We present an annotation study on a representative dataset of literal and idiomatic uses of German infinitive-verb compounds in newspaper and journal texts. Expand
  • 5
  • 3
  • PDF
UdS-(retrain|distributional|surface): Improving POS Tagging for OOV Words in German CMC and Web Data
TLDR
We present in this paper our three system submissions for the POS tagging subtask of the Empirist Shared Task: Our baseline systemUdS-retrain extends a standard training dataset with in-domain training data; UdSdistributional and UdS-surface add two different ways of handling OOV words on top of the baseline system. Expand
  • 6
  • 2
  • PDF
Comprehensive Supersense Disambiguation of English Prepositions and Possessives
TLDR
This paper introduced a new approach to comprehensive analysis of the semantics of prepositions and possessives in English, backed by a thoroughly documented hierarchy and annotated corpus. Expand
  • 26
  • 1
  • PDF
Adposition and Case Supersenses v2.5: Guidelines for English
TLDR
This document offers a detailed linguistic description of SNACS (Semantic Network of Adposition and Case Supersenses; Schneider et al., 2018), an inventory of 50 semantic labels ("supersenses") that characterize the use of adpositions and case markers at a somewhat coarse level of granularity, as demonstrated in the STREUSLE corpus (this https URL version 4.3 tracks guidelines version 2.5). Expand
  • 9
  • 1
  • PDF
Semantically Constrained Multilayer Annotation: The Case of Coreference
TLDR
We propose a coreference annotation scheme 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. Expand
  • 6
  • 1
  • PDF
Unsupervised Induction of Part-of-Speech Information for OOV Words in German Internet Forum Posts
We show that the accuracy of part-ofspeech (POS) tagging of German Internet forum posts can be improved substantially by exploiting distributional similarity information about out-of-vocabulary (OOV)Expand
  • 7
  • PDF
Made for Each Other: Broad-coverage Semantic Structures Meet Preposition Supersenses
TLDR
We show that UCCA and SNACS are compatible and can be combined in a single semantic graph. Expand
  • 3
  • PDF
Comparison by Conversion: Reverse-Engineering UCCA from Syntax and Lexical Semantics
TLDR
We evaluate the mapping between meaning representations from different frameworks using two complementary methods: a rule-based converter, and a supervised delexicalized parser that parses to one framework using only information from the other as features. Expand
  • 1
  • PDF
Supertagging the Long Tail with Tree-Structured Decoding of Complex Categories
TLDR
We investigate constructive models that account for this internal structure that will drive the syntactic derivation during parsing, including novel methods for tree-structured prediction. Expand
Cross-lingual Semantic Representation for NLP with UCCA
TLDR
This is an introductory tutorial to UCCA (Universal Conceptual Cognitive Annotation), a cross-linguistically applicable framework for semantic representation, with corpora annotated in English, German and French. Expand
  • 1
  • PDF