Multilingual summarization system based on analyzing the discourse structure at MultiLing 2013

نویسندگان

  • Daniel Anechitei
  • Eugen Ignat
چکیده

This paper describes the architecture of UAIC 1 ’s Summarization system participating at MultiLing – 2013. The architecture includes language independent text processing modules, but also modules that are adapted for one language or another. In our experiments, the languages under consideration are Bulgarian, German, Greek, English, and Romanian. Our method exploits the cohesion and coherence properties of texts to build discourse structures. The output of the parsing process is used to extract general summaries.

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

MultiLing 2013 MultiLing 2013: Multilingual Multi-document Summarization

This document overviews the strategy, effort and aftermath of the MultiLing 2013 multilingual summarization data collection. We describe how the Data Contributors of MultiLing collected and generated a multilingual multi-document summarization corpus on 10 different languages: Arabic, Chinese, Czech, English, French, Greek, Hebrew, Hindi, Romanian and Spanish. We discuss the rationale behind th...

متن کامل

CIST System Report for ACL MultiLing 2013 ‐ Track 1: Multilingual Multi-document Summarization

This report provides a description of the methods applied in CIST system participating ACL MultiLing 2013. Summarization is based on sentence extraction. hLDA topic model is adopted for multilingual multi-document modeling. Various features are combined to evaluate and extract candidate summary sentences.

متن کامل

Multi-document multilingual summarization corpus preparation, Part 1: Arabic, English, Greek, Chinese, Romanian

This document overviews the strategy, effort and aftermath of the MultiLing 2013 multilingual summarization data collection. We describe how the Data Contributors of MultiLing collected and generated a multilingual multi-document summarization corpus on 10 different languages: Arabic, Chinese, Czech, English, French, Greek, Hebrew, Hindi, Romanian and Spanish. We discuss the rationale behind th...

متن کامل

ACL 2013 MultiLing Pilot Overview

The 2013 Association for Computational Linguistics MultiLing Pilot posed a task to measure the performance of multilingual, single-document, summarization systems using a dataset derived from many Wikipedias. The objective of the pilot was to assess automatic summarization of multilingual text documents outside the news domain and the potential of using Wikipedia articles for such research. Thi...

متن کامل

Multilingual Single-Document Summarization with MUSE

MUltilingual Sentence Extractor (MUSE) is aimed at multilingual single-document summarization. MUSE implements a supervised language-independent summarization approach based on optimization of multiple sentence ranking methods using a Genetic Algorithm. The main advantage of MUSE is its language-independency – it is using statistical sentence features, which can be calculated for sentences in a...

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 2013