Yayınlanmış 1 Ocak 2016 | Sürüm v1
Konferans bildirisi Açık

Sentence Similarity based on Dependency Tree Kernels for Multi-document Summarization

  • 1. Bogazici Univ, Dept Comp Engn, TR-34342 Istanbul, Turkey
  • 2. Univ Michigan, Dept EECS, 3917 Beyster Bldg, Ann Arbor, MI 48109 USA

Açıklama

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.

Dosyalar

bib-073bfeaa-a21a-44b7-a5a0-5eed833670ab.txt

Dosyalar (208 Bytes)

Ad Boyut Hepisini indir
md5:dff4b4f4baccc8fe3fa3b283dc657456
208 Bytes Ön İzleme İndir