Sciweavers

933 search results - page 58 / 187
» Fully automatic cross-associations
Sort
View
COLING
2008
15 years 7 months ago
The Choice of Features for Classification of Verbs in Biomedical Texts
We conduct large-scale experiments to investigate optimal features for classification of verbs in biomedical texts. We introduce a range of feature sets and associated extraction ...
Anna Korhonen, Yuval Krymolowski, Nigel Collier
ZEUS
2010
200views Communications» more  ZEUS 2010»
15 years 7 months ago
On designing a people-oriented constraint-based workflow language
The control-flow of business workflows is characterized by the strict execution order of the activities that is already defined at design time. This well-structured control-flow is...
Frank Leymann, Tobias Unger, Sebastian Wagner
COGSCI
2010
114views more  COGSCI 2010»
15 years 6 months ago
Strudel: A Corpus-Based Semantic Model Based on Properties and Types
Computational models of meaning trained on naturally occurring text successfully model human performance on tasks involving simple similarity measures, but they characterize meani...
Marco Baroni, Brian Murphy, Eduard Barbu, Massimo ...
EMNLP
2010
15 years 4 months ago
PEM: A Paraphrase Evaluation Metric Exploiting Parallel Texts
We present PEM, the first fully automatic metric to evaluate the quality of paraphrases, and consequently, that of paraphrase generation systems. Our metric is based on three crit...
Chang Liu, Daniel Dahlmeier, Hwee Tou Ng
ACL
2012
13 years 8 months ago
Cross-lingual Parse Disambiguation based on Semantic Correspondence
We present a system for cross-lingual parse disambiguation, exploiting the assumption that the meaning of a sentence remains unchanged during translation and the fact that differe...
Lea Frermann, Francis Bond