The ICSI/UTD Summarization System at TAC 2009

نویسندگان

  • Daniel Gillick
  • Benoît Favre
  • Dilek Z. Hakkani-Tür
  • Bernd Bohnet
  • Yang Liu
  • Shasha Xie
چکیده

We describe improvements to our 2008 system that result in a top-performing summarization system. The motivating ideas are (1) improve sentence boundary detection to avoid damaging errors in preprocessing; (2) prune sentences that are unlikely to work well in a summary; (3) leverage sentence position to improve update summarization; (4) focus on high-precision sentence compression to improve readability rather than content.

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

The ICSI Summarization System at TAC 2008

The ICSI multi-document summarization system relies on a general framework that casts summarization as a global optimization problem with an integer linear programming solution. Our primary submission, a simple sentence extractor with an n-gram frequency heuristic, gives results at least as good as any reported on the non-update part of the main task. Our secondary submission adds compressed se...

متن کامل

Description of the LIPN Systems at TAC2009

The Text Analysis Conferences (TAC) offer a unique occasion to show innovative approaches to text summarization. As a first incursion into this new research area, LIPN participated in the Update Summarization task of TAC 2008. The LIPN wanted to improve the results obtained during TAC 2008 and to confirm that the changes made to its summarization system really enhanced the quality of the automa...

متن کامل

The NTNU Summarization System at TAC 2009

In this paper, we presents the results obtained by using a probabilistic summarization framework for the TAC 2009 update summarization task, which has the merits of combining the sentence generative probability and the sentence prior probability for sentence ranking systematically. Especially, each sentence of a document to be summarized is treated as a probabilistic generative model for predic...

متن کامل

Tsinghua University at TAC 2009: Summarizing Multi-documents by Information Distance

This paper presents our extractive summarization systems at the update summarization track of TAC 2009. This system is based on our newly developed document summarization framework under the theory of conditional information distance among many objects. The best summary is defined in this paper to be the one which has the minimum information distance to the entire document set. The best update ...

متن کامل

Obtaining Uncertainty to Generate Summarization

This paper describes Huazhong Normal University’s participation in TAC 2010. For the guided summarization task, we use a better basic summarization system which makes many improvements to the method we used in TAC 2009. Our system is based on uncertainty methods, including cloud. Our teams IDs are 6 and 23, and they are among the best of all the 43 automatic summarization systems in TAC 2010.

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 2009