Summary of the paper

Title Sentence Similarity based on Dependency Tree Kernels for Multi-document Summarization
Authors Şaziye Betül Özateş, Arzucan Özgür and Dragomir Radev
Abstract We introduce an approach based on using the dependency grammar representations of sentences to compute sentence similarity for extractive multi-document summarization. We adapt and investigate the effects of two untyped dependency tree kernels, which have originally been proposed for relation extraction, to the multi-document summarization problem. In addition, we propose a series of novel dependency grammar based kernels to better represent the syntactic and semantic similarities among the sentences. The proposed methods incorporate the type information of the dependency relations for sentence similarity calculation. To our knowledge, this is the first study that investigates using dependency tree based sentence similarity for multi-document summarization.
Topics Summarisation, Text Mining, Grammar and Syntax
Full paper Sentence Similarity based on Dependency Tree Kernels for Multi-document Summarization
Bibtex @InProceedings{ZATE16.617,
  author = {Şaziye Betül Özateş and Arzucan Özgür and Dragomir Radev},
  title = {Sentence Similarity based on Dependency Tree Kernels for Multi-document Summarization},
  booktitle = {Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016)},
  year = {2016},
  month = {may},
  date = {23-28},
  location = {Portoro┼ż, Slovenia},
  editor = {Nicoletta Calzolari (Conference Chair) and Khalid Choukri and Thierry Declerck and Sara Goggi and Marko Grobelnik and Bente Maegaard and Joseph Mariani and Helene Mazo and Asuncion Moreno and Jan Odijk and Stelios Piperidis},
  publisher = {European Language Resources Association (ELRA)},
  address = {Paris, France},
  isbn = {978-2-9517408-9-1},
  language = {english}
 }
Powered by ELDA © 2016 ELDA/ELRA