BioChain : Using Lexical Chaining Methods for Biomedical Text Summarization

1 ABSTRACT Lexical chaining is a technique for identifying sem antically-related terms in a text. It is useful in document summarization in order to identify the top sentences most likely to contain the main ideas of a document or document set. These top sentences are t hen xtracted and combined in order to produce a summary of the document(s). To date, summarization w rk using lexical chains has been done using general purpose texts, such as news items, in combi nation with lexical resources, such as WordNet. To implement biomedical document summarization using l exical chaining, a chaining algorithm must first be implemented using biomedical lexical resources. The Unified Medical Language System (UMLS) provides resources, such as metathesaurus and seman tic network, as well as the text-to-concept mapping tool MetaMap Transfer, which are expected to be use ful for implementing chaining in the biomedical domain. The goal of the project is to produce a nov el concept chaining implementation in the biomedica l domain using UMLS lexicon and the ideas of lexical chaining. The results of chaining text concepts based on semantic types are then applied to biomedi cal ocument summarization, using both abstracts and full-text.

[1]  Peter D. Turney.  Learning Algorithms for Keyphrase Extraction , 2000, Information Retrieval.

[2]  Alan R. Aronson,et al.  Effective mapping of biomedical text to the UMLS Metathesaurus: the MetaMap program , 2001, AMIA.

[3]  Eamonn Newman,et al.  News Story Gisting at University College Dublin , 2004 .

[4]  佚名,et al.  用Microsoft Word制作 精彩贺卡 , 2000 .

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

[6]  Panagiotis Stamatopoulos,et al.  Summarization from Medical Documents: A Survey , 2005, Artif. Intell. Medicine.

[7]  B. Magnini,et al.  Keyphrase Extraction for Summarization Purposes : The LAKE System at DUC-2004 , 2004 .

[8]  Andrew Hickl,et al.  Lite-GISTexter at DUC 2005 , 2005 .

[9]  Kenneth C. Litkowski,et al.  Summarization Experiments in DUC 2004 , 2004 .

[10]  John Dunnion,et al.  Comparing Lexical Chain-based Summarisation Approaches Using an Extrinsic Evaluation , 2004 .

[11]  Kathleen F. McCoy,et al.  Efficiently Computed Lexical Chains as an Intermediate Representation for Automatic Text Summarization , 2002, CL.

[12]  Kathleen McKeown,et al.  Improving Word Sense Disambiguation in Lexical Chaining , 2003, IJCAI.

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

[14]  Graeme Hirst,et al.  Lexical Cohesion Computed by Thesaural relations as an indicator of the structure of text , 1991, CL.