Corpus ID: 59835348

Intrinsic Evaluation of Generic News Text Summarization Systems

@inproceedings{Over2003IntrinsicEO,
  title={Intrinsic Evaluation of Generic News Text Summarization Systems},
  author={P. Over},
  year={2003}
}
  • P. Over
  • Published 2003
  • Computer Science
Content Selection in Deep Learning Models of Summarization
TLDR
It is suggested that it is easier to create a summarizer for a new domain than previous work suggests and the benefit of deep learning models for summarization for those domains that do have massive datasets is brought into question. Expand
A Context-Based Word Indexing Model for Document Summarization
TLDR
A context sensitive document indexing model based on the Bernoulli model of randomness, using the lexical association between terms to give a context sensitive weight to the document terms has been proposed. Expand
Automatic text summarization using lexical chains : algorithms and experiments
TLDR
A lexical chaining method that includes the glossary relations in the chaining process enables us to identify topically related concepts, for instance dormitory and student, and thereby enhances the identification of cohesive ties in the text. Expand
Cross-lingual C*ST*RD: English access to Hindi information
TLDR
Various possible configurations, with different tradeoffs in processing speed and ease of use, enable the rapid deployment of C*ST*RD to new languages under various conditions. Expand
Information Preparation with the Human in the Loop
TLDR
This thesis proposes an interactive summarization loop to iteratively create and refine multi-document summaries based on the users’ feedback and investigates sampling strategies based on active machine learning and joint optimization to reduce the number of iterations and the amount of user feedback required. Expand
Towards Context-free Information Importance Estimation
TLDR
The guiding hypothesis of this work is that prior methods for automatic information importance estimation are inherently limited because they are based on merely correlated signals that are, however, not causally linked with information importance, so a fundamentally new approach for importance estimation is needed. Expand
TopicRank : ordonnancement de sujets pour l'extraction automatique de termes-clés
TLDR
Dans cet article nous presentons TopicRank, une methode non supervisee a base de graphe pour l’extraction de termes-cles, un methode groupe les terme-cles candidats en sujets, ordonne les suJets et extrait de chacun des meilleurs su jets le terme-cle candidat qui le represente le mieux. Expand
WordTopic-MultiRank: A New Method for Automatic Keyphrase Extraction
TLDR
This work proposes WordTopic-MultiRank as a new method for keyphrase extraction, based on the idea that words relate with each other via multiple relations, and treats various latent topics in documents as heterogeneous relations between words and construct a multi-relational word network. Expand
Extractive summarization using a latent variable model
TLDR
A generative approach to explicitly identify summary and non-summary topic distributions in the sentences of a given set of documents using approximate summary topic probabilities as latent output variables to build a discriminative classifier model. Expand
Experiments in DUC 2005
TLDR
A brief overview of the summarization system, which took part in DUC 2005 evaluation workshop, and the objective of this year’s workshop is to model a real-world information need, and parallely focus on development of a stable and reliable evaluation procedure. Expand
...
1
2
3
4
5
...