![]() ![]() These results are further described in this article and in his Masters Thesis. When we used the same translation system as the other participants, Lakhas' results were by far the best. ![]() Although Lakhas followed a different track from the one proposed by the DUC organizers, its evaluation results were among the best ones at DUC2004. These Arabic summaries were then translated automatically into English. Lakhas has also been adapted for producing very short summaries (about ten words) for the DUC2004 evaluation. Lakhasįouad Douzidia has developed Lakhas (meaning summarize in Arabic), a summarization system for newspaper-type articles in Arabic based on a combination of methods that have only been used until now in English. CATS' performance, described in this article, was excellent compared with the thirty other systems that participated to the competition. The summary had to address a specific topic defined by question written in about 20 lines. The task was to summarize in less than 250 words clusters of about 20 newspaper type articles dealing with similar events. CATSĬATS (Cats is an Automatic Text Summarizer) has been developed by Atefeh Farzindar and Frédérik Rozon during the summer of 2005 to take part in the Document Understanting Conference 2005 ( DUC2005) competition. For DUC2003, SumUM was again modified to deal with the summarization of multiple documents and again it scored very well. ![]() Although the system was applied to a different type of text than the newspaper articles used for development, SumUM 's scores were among the best at DUC2002. Papers dealing with SumUM and more of Horacio Saggion workįor the DUC2002 summary evaluation competition, Atefeh Farzindar slightly modified SumUM without changing the algorithms or the syntactic patterns that were manually developed from a corpus study.During evaluations, these have been found to be of comparable quality to summaries written by authors. The output of the system is a short indicative summary which is generated from information found in the original text. The input to the system is a scientific article in English, containing the following structural elements: title, author and affiliation, introduction, main sections, conclusion, references and acknowledgments. SumUM produces a summary in two steps: first an indicative summary, which identifies important subjects of a document then an informative summary is produced which elaborates a few subjects selected by the user. SumUM produces short summaries (10-15 lines) of long scientific documents (15-20 pages). Horacio is now working as Ramon y Cajal Senior Research Fellow in the TALN Group at the Department of Information and Communication Technologies, Universitat Pompeu Fabra in Barcelona. SumUM was developed by Horacio Saggion in his Ph.D. From 2014 to 2017, Bruno Malenfant worked on citation based summarization.thesis, from 2010 to 2013, Pierre-Étienne Genest worked on abstractive summarization. In 2009, RALI and NLP Technologies continued their collaboration with the ISASLI project.In 2007-2008, RALI in collaboration with NLP Technologies took part in the ASLI project dealing in great part on the automatic summarization of judgments.LetSUM started a series of works on judicial documents.Lakhas dealt with newspaper type documents in Arabic.SumUM was then adapted for CATS to summarize clusters of documents.Horacio Saggion, in the late nineties, developed SumUM for summarizing scientific articles.Since 2002, RALI has participated in multiple competitions of Document Understanding Conference (DUC), more recently Text Analysis Conference (TAC). Researchers at RALI, under the direction of Guy Lapalme, have been working in automatic summarization for many years. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |