Sentence Similarity based on Dependency Tree Kernels for Multi-document Summarization
نویسندگان
چکیده
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.
منابع مشابه
TLR at DUC: Tree similarity
We provide a solution to this year’s task of a question-based multi-document summarization by employing tree similarity of the dependency parse trees for reformulated questions and candidate sentences.
متن کاملSingle Document Summarization based on Nested Tree Structure
Many methods of text summarization combining sentence selection and sentence compression have recently been proposed. Although the dependency between words has been used in most of these methods, the dependency between sentences, i.e., rhetorical structures, has not been exploited in such joint methods. We used both dependency between words and dependency between sentences by constructing a nes...
متن کاملDependency-based Sentence Alignment for Multiple Document Summarization
In this paper, we describe a method of automatic sentence alignment for building extracts from abstracts in automatic summarization research. Our method is based on two steps. First, we introduce the “dependency tree path” (DTP). Next, we calculate the similarity between DTPs based on the ESK (Extended String Subsequence Kernel), which considers sequential patterns. By using these procedures, w...
متن کاملResults of CRL/NYU System at DUC-2003 and an Experiment on Division of Document Sets
We participated in three multi-document summarization tasks at the DUC-2003 formal run and evaluated the performance of our summarization system. Our summarization system based on sentence extraction also incorporated a module to estimate similarity between sentences for multi-document summarization. The similarity information was used for selecting the representative sentence among similar sen...
متن کاملAutomatic Multi-document Summarization Based on New Sentence Similarity Measures
The acquiring of sentence similarity has become a crucial step in graph-based multi-document summarization algorithms which have been intensively studied during the past decade. Previous algorithms generally considered sentence-level structure information and semantic similarity separately, which, consequently, had no access to grab similarity information comprehensively. In this paper, we pres...
متن کامل