Artificial Intelligence - Special volume on natural language processing
Sentence level discourse parsing using syntactic and lexical information
NAACL '03 Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology - Volume 1
SemEval'07 task 19: frame semantic structure extraction
SemEval '07 Proceedings of the 4th International Workshop on Semantic Evaluations
Introduction to the CoNLL-2005 shared task: semantic role labeling
CONLL '05 Proceedings of the Ninth Conference on Computational Natural Language Learning
Hi-index | 0.00 |
The recently started SEASIDE project is funded for five years (2008--2013) by the German Excellence Initiative as part of Saarland University's Cluster of Excellence on "Multimodal Computing and Interaction". In the project, we aim to bring together two active research areas which both deal with "computing meaning" but currently stand more or less independently next to each other: discourse processing and computation of semantic argument structure. We expect that both areas will benefit from this: semantic argument information will allow for a more sophisticated representation of discourse meaning, while discourse information can also be beneficial for systems which compute semantic argument structure (i.e. semantic role labellers). Eventually we aim for an incremental model of text meaning which can be computed in a robust, data-driven way by utilising and combining information from several levels of linguistic analysis. The model should be sophisticated enough to aid applications such as text mining, information extraction, question answering, and text summarisation.