Semantic argument frequency-based Multi-Document Summarization
2009 24th International Symposium on Computer and Information Sciences, ISCIS 2009
Please cite this item using this persistent URLhttp://hdl.handle.net/11693/28644
Semantic Role Labeling (SRL) aims to identify the constituents of a sentence, together with their roles with respect to the sentence predicates. In this paper, we introduce and assess the idea of using SRL on generic Multi-Document Summarization (MDS). We score sentences according to their inclusion of frequent semantic phrases and form the summary using the top-scored sentences. We compare this method with a term-based sentence scoring approach to investigate the effects of using semantic units instead of single words for sentence scoring. We also integrate our scoring metric as an auxiliary feature to a cutting edge summarizer with the intention of examining its effects on the performance. The experiments using datasets from the Document Understanding Conference (DUC) 2004 show that the SRL-based summarization outperforms the term-based approach as well as most of the DUC participants. © 2009 IEEE.
- Conference Paper 
Showing items related by title, author, creator and subject.
Duygulu P.; Baştan, M. (2011)The semantic gap problem, which can be referred to as the disconnection between low-level multimedia data and high-level semantics, is an important obstacle to build real-world multimedia systems. The recently developed ...
Semantic similarity between Turkish and European languages using word embeddings [Türkçe ile Avrupa Dilleri Arasindaki Anlamsal Benzerliǧin Kelime Temsilleri ile Gösterimi] Sjenel L.K.; Yucesoy V.; Koc A.; Cukur T. (Institute of Electrical and Electronics Engineers Inc., 2017)Representation of words coming from vocabulary of a language as real vectors in a high dimensional space is called as word embeddings. Word embeddings are proven to be successful in modelling semantic relations between ...
Çavuş Ö.; Aksoy, S. (2008)We describe an annotation and retrieval framework that uses a semantic image representation by contextual modeling of images using occurrence probabilities of concepts and objects. First, images are segmented into regions ...