poster

Learning to generate summary as structured output

Authors:

Hiroya Takamura,

Manabu OkumuraAuthors Info & Claims

CIKM '10: Proceedings of the 19th ACM international conference on Information and knowledge management

Pages 1437 - 1440

https://doi.org/10.1145/1871437.1871641

Published: 26 October 2010 Publication History

Get Access

Abstract

We propose to use a structured output learning for summary generation based on the maximum coverage problem. Our method learns a function that outputs the benefit of each conceptual unit in the document cluster for this summarization model. In the training, we iteratively run a greedy algorithm that accepts items (sentences) with different costs (length) in order to generate a summary within the given maximum length limit. We empirically show that the structured output learning works well for this task and also examine its behavior in several dierent settings.

References

[1]

J. M. Conroy, J. D. Schlesinger, J. Goldstein, and D. P. O'Leary. Left-brain/right-brain multi-document summarization. DUC, 2004.

Google Scholar

[2]

Document Understanding Conference 2003.

Google Scholar

[3]

Document Understanding Conference 2004.

Google Scholar

[4]

E. Filatova and V. Hatzivassiloglou. A formal model for information selection in multi-sentence text extraction. COLING, pages 397--403, 2004.

Digital Library

Google Scholar

[5]

T. Joachims, T. Finley, and C.-N. J. Yu. Cutting-plane training of structural SVMs. Machine Learning, 77(1):27--59, 2009.

Digital Library

Google Scholar

[6]

S. Khuller, A. Moss, and J. S. Naor. The budgeted maximum coverage problem. Information Processing Letters, 70(1):39--45, 1999.

Digital Library

Google Scholar

[7]

C. Lin. ROUGE: a package for automatic evaluation of summaries. Workshop on Text Summarization Branches Out, pages 74--81, 2004.

Google Scholar

[8]

I. Mani. Automatic Summarization. John Benjamins Publisher, 2001.

Google Scholar

[9]

H. Takamura and M. Okumura. Text summarization model based on maximum coverage problem and its variant. EACL, pages 781--789, 2009.

Digital Library

Google Scholar

[10]

I. Tsochantaridis, T. Joachims, T. Hofmann, and Y. Altun. Large margin methods for structured and interdependent output variables. JMLR, 6:1453--1484, 2005.

Digital Library

Google Scholar

[11]

W. Yih, J. Goodman, L. Vanderwende, and H. Suzuki. Multi-document summarization by maximizing informative content-words. IJCAI, pages 1776--1782, 2007.

Digital Library

Google Scholar

[12]

Y. Yue and T. Joachims. Predicting diverse subsets using structural SVMs. ICML, pages 1224--1231, 2008.

Digital Library

Google Scholar

Cited By

View all

Avinesh PPeyrard MMeyer C(2021)Live blog summarizationLanguage Resources and Evaluation10.1007/s10579-020-09513-5Online publication date: 2-Jan-2021
https://doi.org/10.1007/s10579-020-09513-5
Chowdhury TChakraborty TDey LChaudhury SKrishnapuram RSingla PRoy R(2019)CQASUMMProceedings of the ACM India Joint International Conference on Data Science and Management of Data10.1145/3297001.3297004(18-26)Online publication date: 3-Jan-2019
https://dl.acm.org/doi/10.1145/3297001.3297004
Kikuchi YWatanabe ARyohei STakamura HOkumura M(2016)Learning from numerous untailored summariesProceedings of the 14th Pacific Rim International Conference on Trends in Artificial Intelligence10.1007/978-3-319-42911-3_17(206-219)Online publication date: 22-Aug-2016
https://dl.acm.org/doi/10.1007/978-3-319-42911-3_17

Index Terms

Learning to generate summary as structured output
1. Computing methodologies
  1. Artificial intelligence
    1. Natural language processing
      1. Natural language generation

Recommendations

Manifold regularization in structured output space for semi-supervised structured output prediction

Structured output prediction aims to learn a predictor to predict a structured output from a input data vector . The structured outputs include vector, tree, sequence, etc. We usually assume that we have a training set of input---output pairs to train ...
Learning from structured data with high dimensional structured input and output domain
An extract-then-abstract based method to generate disaster-news headlines using a DNN extractor followed by a transformer abstractor
Abstract
Generating news headlines has been one of the predominant problems in Natural Language Processing research. Modern transformer models, if fine-tuned, can present a good headline with attention to all the parts of a disaster-news ...
Highlights
- Proposed an extract-then-abstract based disaster-news headline generation approach.

Comments

Information & Contributors

Information

Published In

CIKM '10: Proceedings of the 19th ACM international conference on Information and knowledge management

October 2010

2036 pages

ISBN:9781450300995

DOI:10.1145/1871437

General Chair:
Jimmy Huang
York University, Canada
,
Program Chairs:
Nick Koudas
University of Toronto, Canada
,
Gareth Jones
Dublin City University, Ireland
,
Xindong Wu
University of Vermont, USA
,
Kevyn Collins-Thompson
Microsoft Research, USA
,
Aijun An
York University, Canada

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 26 October 2010

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tag

text summarization

Qualifiers

Poster

Conference

CIKM '10

Sponsor:

CIKM '10: International Conference on Information and Knowledge Management

October 26 - 30, 2010

ON, Toronto, Canada

Acceptance Rates

Overall Acceptance Rate 1,861 of 8,427 submissions, 22%

Upcoming Conference

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

3
Total Citations
View Citations
350
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 04 Oct 2024

Other Metrics

View Author Metrics

Citations

Cited By

View all

Avinesh PPeyrard MMeyer C(2021)Live blog summarizationLanguage Resources and Evaluation10.1007/s10579-020-09513-5Online publication date: 2-Jan-2021
https://doi.org/10.1007/s10579-020-09513-5
Chowdhury TChakraborty TDey LChaudhury SKrishnapuram RSingla PRoy R(2019)CQASUMMProceedings of the ACM India Joint International Conference on Data Science and Management of Data10.1145/3297001.3297004(18-26)Online publication date: 3-Jan-2019
https://dl.acm.org/doi/10.1145/3297001.3297004
Kikuchi YWatanabe ARyohei STakamura HOkumura M(2016)Learning from numerous untailored summariesProceedings of the 14th Pacific Rim International Conference on Trends in Artificial Intelligence10.1007/978-3-319-42911-3_17(206-219)Online publication date: 22-Aug-2016
https://dl.acm.org/doi/10.1007/978-3-319-42911-3_17

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Cited By

Index Terms

Recommendations

Manifold regularization in structured output space for semi-supervised structured output prediction

Learning from structured data with high dimensional structured input and output domain

An extract-then-abstract based method to generate disaster-news headlines using a DNN extractor followed by a transformer abstractor