Approximation algorithms for NP-hard problems
Summarizing scientific articles: experiments with relevance and rhetorical status
Computational Linguistics - Summarization
Generating indicative-informative summaries with sumUM
Computational Linguistics - Summarization
The Journal of Machine Learning Research
Multidocument summarization via information extraction
HLT '01 Proceedings of the first international conference on Human language technology research
Selecting sentences for multidocument summaries using randomized local search
AS '02 Proceedings of the ACL-02 Workshop on Automatic Summarization - Volume 4
Language independent NER using a maximum entropy tagger
CONLL '03 Proceedings of the seventh conference on Natural language learning at HLT-NAACL 2003 - Volume 4
Automatic summarising: The state of the art
Information Processing and Management: an International Journal
Extractive summarization using supervised and semi-supervised learning
COLING '08 Proceedings of the 22nd International Conference on Computational Linguistics - Volume 1
The automatic creation of literature abstracts
IBM Journal of Research and Development
Automatically generating extraction patterns from untagged text
AAAI'96 Proceedings of the thirteenth national conference on Artificial intelligence - Volume 2
Towards a unified approach to simultaneous single-document and multi-document summarizations
COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics
Learning web query patterns for imitating Wikipedia articles
COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics: Posters
Datasets for generic relation extraction*
Natural Language Engineering
Focused meeting summarization via unsupervised relation extraction
SIGDIAL '12 Proceedings of the 13th Annual Meeting of the Special Interest Group on Discourse and Dialogue
Hi-index | 0.00 |
Experiments are reported that investigate the effect of various source document representations on the accuracy of the sentence extraction phase of a multi-document summarisation task. A novel representation is introduced based on generic relation extraction (GRE), which aims to build systems for relation identification and characterisation that can be transferred across domains and tasks without modification of model parameters. Results demonstrate performance that is significantly higher than a non-trivial baseline that uses tf*idf-weighted words and at least as good as a comparable but less general approach from the literature. Analysis shows that the representations compared are complementary, suggesting that extraction performance could be further improved through system combination.