Scaling and Semantically-Enriching Language-Agnostic Summarization

Author:

Giannakopoulos George1ORCID,Kiomourtzis George2,Pittaras Nikiforos3,Karkaletsis Vangelis4

Affiliation:

1. NCSR Demokritos, Greece & SciFY PNPC, Greece

2. SciFY PNPC, Greece & NCSR Demokritos, Greece

3. NCSR Demokritos, Greece & National and Kapodistrian University of Athens, Greece

4. NCSR Demokritos, Greece

Abstract

This chapter describes the evolution of a real, multi-document, multilingual news summarization methodology and application, named NewSum, the research problems behind it, as well as the steps taken to solve these problems. The system uses the representation of n-gram graphs to perform sentence selection and redundancy removal towards summary generation. In addition, it tackles problems related to topic and subtopic detection (via clustering), demonstrates multi-lingual applicability, and—through recent advances—scalability to big data. Furthermore, recent developments over the algorithm allow it to utilize semantic information to better identify and outline events, so as to offer an overall improvement over the base approach.

Publisher

IGI Global

Reference99 articles.

1. Afantenos, S. D., Doura, I., Kapellou, E., & Karkaletsis, V. (2004). Exploiting Cross-Document Relations for Multi-Document Evolving Summarization. Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science), 3025, 410–419.

2. Aker, A., Celli, F., Funk, A., Kurtic, E., Hepple, M., & Gaizauskas, R. (2016). Sheffield-Trento System for Sentiment and Argument Structure Enhanced Comment-to-Article Linking in the Online News Domain. Academic Press.

3. Retrieval and novelty detection at the sentence level

4. Angheluta, R., De Busser, R., & Moens, M.-F. (2002). The use of topic segmentation for automatic summarization. In Proceedings of the ACL-2002 Workshop on Automatic Summarization. Retrieved from https://www.law.kuleuven.be/icri/publications/51DUC2002.pdf

5. AllSummarizer system at MultiLing 2015: Multilingual single and multi-document summarization

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3