Single-document summarization and multidocument summarization are very closely related tasks and they have been widely investigated independently. This paper examines the mutual i...
Martins et al. (2008) presented what to the best of our knowledge still ranks as the best overall result on the CONLLX Shared Task datasets. The paper shows how triads of stacked ...
We propose semantic role features for a Tree-to-String transducer to model the reordering/deletion of source-side semantic roles. These semantic features, as well as the Tree-to-S...
Information Extraction (IE) technology is facing new challenges of dealing with large-scale heterogeneous data sources from different documents, languages and modalities. Informat...
We propose a methodology for investigating how well NLP systems handle meaning preserving syntactic variations. We start by presenting a method for the semi automated creation of ...