CLASSY 2009: Summarization and Metrics
نویسندگان
چکیده
This year the CLASSY team participated in the update summary task and made four submissions to summarization evaluation (AESOP). Our AESOP submissions used combinations of ROUGE scores along with an update (or newness) score. We also use these new metrics, which we call Nouveau ROUGE, to help train our system and evaluate new ideas on computing update summaries. CLASSY (Clustering, Linguistics, and Statistics for Summarization Yield) is the summarization system developed mainly1 by IDA/Center for Computing Sciences. Before describing the Nouveau ROUGE update metrics, we describe improvements made to CLASSY in data preparation, redundancy removal, and sentence selection.
منابع مشابه
Guiding CLASSY Toward More Responsive Summaries
We discuss changes and improvements in CLASSY for TAC 2010 along with a set of evaluation metrics. Results for both summarization and AESOP evaluation are given.
متن کاملCLASSY 2011 at TAC: Guided and Multi-lingual Summaries and Evaluation Metrics
We present CLASSY’s guided summarization as well as multi-lingual methods as submitted to TAC 2011. In addition, we describe improved metrics submitted to the AESOP task at TAC.
متن کاملAssessing the Effect of Inconsistent Assessors on Summarization Evaluation
We investigate the consistency of human assessors involved in summarization evaluation to understand its effect on system ranking and automatic evaluation techniques. Using Text Analysis Conference data, we measure annotator consistency based on human scoring of summaries for Responsiveness, Readability, and Pyramid scoring. We identify inconsistencies in the data and measure to what extent the...
متن کاملArabic/English Multi-document Summarization with CLASSY - The Past and the Future
Automatic document summarization has become increasingly important due to the quantity of written material generated worldwide. Generating good quality summaries enables users to cope with larger amounts of information. English-document summarization is a difficult task. Yet it is not sufficient. Environmental, economic, and other global issues make it imperative for English speakers to underst...
متن کاملCLASSY and TAC 2008 Metrics
We present results of CLASSY’s submissions to TAC 2008 update and blog opinion summarization tasks. Additionally, we evaluate and analyze many of the results for all of the systems participating in each of these tasks.
متن کامل