Generic text summarization for Turkish

In this paper, we propose a generic text summarization method that generates summaries of Turkish texts by ranking sentences according to their scores calculated using their surface level features and extracting the highest ranked ones from the original documents. In order to extract sentences which form a summary with an extensive coverage of main content of the text and less redundancy, we use the features such as term frequency, key phrase, centrality, title similarity and position of the sentence in the original text. Sentence rank is computed using a score function that uses its feature values and the weights of the features. The best feature weights are learned using machine learning techniques with the help of human constructed summaries. Performance evaluation is conducted by comparing summarization outputs with manual summaries generated by 25 independent human evaluators. This paper presents one of the first Turkish summarization systems, and its results are promising.

[1]  Hans Peter Luhn,et al.  The Automatic Creation of Literature Abstracts , 1958, IBM J. Res. Dev..

[2]  Chin-Yew Lin.  Training a selection function for extraction , 1999, CIKM '99.

[3]  Rada Mihalcea,et al.  TextRank: Bringing Order into Text , 2004, EMNLP.

[4]  Inderjeet Mani,et al.  Summarizing Similarities and Differences Among Related Documents , 1997, Information Retrieval.

[5]  Dragomir R. Radev,et al.  LexRank: Graph-based Centrality as Salience in Text Summarization , 2004 .

[6]  Eduard Hovy,et al.  Automated Text Summarization in SUMMARIST , 1997, ACL 1997.

[7]  Eduard H. Hovy,et al.  Automated Text Summarization and the SUMMARIST System , 1998, TIPSTER.

[8]  Rada Mihalcea,et al.  Language Independent Extractive Summarization , 2005, ACL.

[9]  Eduard H. Hovy,et al.  Automatic Evaluation of Summaries Using N-gram Co-occurrence Statistics , 2003, NAACL.

[10]  John Dunnion,et al.  Assessing the Impact of Lexical Chain Scoring Methods and Sentence Extraction Schemes on Summarization , 2004, CICLing.

[11]  Inderjeet Mani,et al.  The Challenges of Automatic Summarization , 2000, Computer.

[12]  Wei-Pang Yang,et al.  Text summarization using a trainable summarizer and latent semantic analysis , 2005, Inf. Process. Manag..

[13]  Ilyas Cicekli,et al.  Lexical Cohesion Based Topic Modeling for Summarization , 2008, CICLing.

[14]  Horacio Saggion,et al.  Generating Indicative-Informative Summaries with SumUM , 2002, Computational Linguistics.

[15]  I. Cicekli,et al.  TurKeyX: Turkish keyphrase extractor , 2008, 2008 23rd International Symposium on Computer and Information Sciences.

[16]  Regina Barzilay,et al.  Using Lexical Chains for Text Summarization , 1997 .

[17]  Xin Liu,et al.  Generic text summarization using relevance measure and latent semantic analysis , 2001, SIGIR '01.

[18]  Yllias Chali,et al.  Text Summarization Using Lexical Chains , 2001 .

[19]  Kathleen R. McKeown,et al.  Generating natural language summaries from multiple on-line sources , 1998 .