Summarization Techniques at DUC 2004
نویسندگان
چکیده
This paper presents the summarization techniques implemented by the University of Lethbridge summarizer in order to generate very short summary ( 75 bytes) and short summary ( 665 bytes) from single and multiple documents. We present these techniques in the context of DUC 2004.
منابع مشابه
CRL/NYU Summarization System at DUC-2004
We participated in two multi-document summarization tasks (Task 2 and Task 5) at the DUC-2004 formal run and evaluated the performance of our summarization system. Our system based on sentence extraction also uses a module to estimate similarity between sentences. The similarity information was used for either selecting the representative sentence among similar sentences or gathering key senten...
متن کاملCRL/NYU System at DUC-2004
We participated in two multi-document summarization tasks (Task 2 and Task 5) at the DUC-2004 formal run and evaluated the performance of our summarization system. Our system based on sentence extraction also uses a module to estimate similarity between sentences. The similarity information was used for either selecting the representative sentence among similar sentences or gathering key senten...
متن کاملThe University of Michigan at DUC 2004
We present the results of Michigan’s participation in DUC 2004. Our system, MEAD, ranked as one of the top systems in four of the five tasks. We introduce our new feature, LexPageRank, a new measure of sentence centrality inspired by the prestige concept in social networks. LexPageRank gave promising results in multi-document summarization. Our approach for Task 5, biographical summarization, w...
متن کاملThe Effects Of Human Variation In DUC Summarization Evaluation
There is a long history of research in automatic text summarization systems by both the text retrieval and the natural language processing communities, but evaluation of such systems’ output has always presented problems. One critical problem remains how to handle the unavoidable variability in human judgments at the core of all the evaluations. Sponsored by the DARPA TIDES project, NIST launch...
متن کاملThe Hong Kong Polytechnic University at DUC2005
This paper discusses the query-based multidocument summarization techniques implemented by the Hong Kong Polytechnic University at DUC 2005. The summarization system is built under the framework of MEAD. In addition to borrow the features provided by MEAD for text summarization, including centroid and sentence length etc., we also introduce the entity-based, pattern-based, termbased and semanti...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2004