• Publications
  • Influence
Multiword Expression Processing: A Survey
TLDR
We propose a conceptual framework within which challenges and research contributions can be positioned. Expand
  • 87
  • 11
  • PDF
PARSEME multilingual corpus of verbal multiword expressions
Agata Savary1, Marie Candito2, Verginica BarbuMititelu3, Eduard Bejček4, Fabienne Cap5, Slavomír Čéplö6, Silvio Ricardo Cordeiro7, Gülşen Eryiğit8, Voula Giouli9, Maarten van Gompel10, YaakovExpand
  • 24
  • 5
  • PDF
Question Answering for Dutch using Dependency Relations
TLDR
Joost is a question answering system for Dutch which makes extensive use of dependency relations. Expand
  • 58
  • 4
  • PDF
Finding Synonyms Using Automatic Word Alignment and Measures of Distributional Similarity
TLDR
We present a method based on automatic word alignment of parallel corpora consisting of documents translated into multiple languages and compare our method with a monolingual syntax-based method. Expand
  • 116
  • 3
  • PDF
Scaling up Automatic Cross-Lingual Semantic Role Annotation
TLDR
We scale up previous efforts by using an automatic approach to semantic annotation that does not rely on a semantic ontology for the target language. Expand
  • 68
  • 3
  • PDF
Cross-Lingual Validity of PropBank in the Manual Annotation of French
TLDR
We show that the PropBank annotation scheme developed for English can be applied cross-lingually. Expand
  • 34
  • 3
  • PDF
The University of Groningen at QA@CLEF 2006: Using Syntactic Knowledge for QA
TLDR
We describe our system for the monolingual Dutch and multilingual English to Dutch QA tasks, which makes heavy use of syntactic information. Expand
  • 17
  • 3
  • PDF
Abstraction and Generalisation in Semantic Role Labels: PropBank, VerbNet or both?
TLDR
Semantic role labels are the representation of the grammatically relevant aspects of a sentence meaning. Expand
  • 47
  • 2
  • PDF
Syntactic Contexts for Finding Semantically Related Words
TLDR
Using Dutch EuroWordNet as evaluation standard, we investigated which vector-based method and which combination of syntactic relations is the strongest predictor of semantic similarity. Expand
  • 36
  • 2
  • PDF
Automatic Acquisition of Lexico-semantic Knowledge for QA
TLDR
We present an experiment for finding semantically similar words on the basis of a parsed corpus of Dutch text and show that the acquired information correlates with relations found in Dutch EuroWordNet. Expand
  • 22
  • 1
  • PDF