NII at the 2006 Multilingual Summarization Evaluation

نویسنده

  • David Kirk Evans
چکیده

In this paper I detail the implementation of an extractionbased summarization system that uses sentence clustering and named entity identification as main features for the 2006 Multilingual Summarization Evaluation. I discuss some of the failings of my system, and what can be done to improve it.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Multilingual Multidocument Summarization Tools and Evaluation

We describe a number of experiments carried out to address the problem of creating summaries from multiple sources in multiple languages. A centroid-based sentence extraction system has been developed which decides the content of the summary using texts in different languages and uses sentences from English sources alone to create the final output. We describe the evaluation of the system in th...

متن کامل

CLASSY Arabic and English Multi-Document Summarization

Our Multilingual Summarization Evaluation entries for MSE-2006 were based upon an improved version of our CLASSY (Clustering, Linguistics, And Statistics for Summarization Yield) system. Our two entries were systems 20 and 21 and represented approaches based upon extracts from a) only English documents and b) English and the translated Arabic documents (full clusters). This paper presents a bri...

متن کامل

Columbia University at Mse 2005

We describe our participation in the Multilingual Summarization Evaluation 2005. We describe the Columbia summarizers that were used in our submission and discuss the evaluation, drawing conclusions about the performance of our summarizers, discussing the state of multilingual summarization in general and also listing issues that need consideration for future evaluations.

متن کامل

PKUSUMSUM : A Java Platform for Multilingual Document Summarization

PKUSUMSUM is a Java platform for multilingual document summarization, and it supports multiple languages, integrates 10 automatic summarization methods, and tackles three typical summarization tasks. The summarization platform has been released and users can easily use and update it. In this paper, we make a brief description of the characteristics, the summarization methods, and the evaluation...

متن کامل

The Future of Multilingual Summarization: Beyond Sentence Extraction

In this paper I present a vision for the future of multilingual summarization that focuses on summarizing differences between documents: generating sentences that explain the main points of controversy in the document set, identifying different sides in the dialogue and the claims they support, and identifying how content differs across document boundaries (cultural, national, political, etc.)....

متن کامل

ذخیره 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 2006