Multidocument Summary Generation
ACM Transactions on Asian Language Information ProcessingPublished 1 February 2008
June‐Jei Kuo, Hsin‐Hsi Chen
Citations21
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
A temporal resolution algorithm is presented, using focusing time and coreference chains, to convert Chinese temporal expressions in a document into calendrical forms to address sentence ordering.
Abstract
Summary generation for multiple documents poses a number of issues including sentence selection, sentence ordering, and sentence reduction over single-document summarization. In addition, the temporal resolution among extracted sentences is also important. This article considers informative words and event words to deal with multidocument summarization. These words indicate the important concepts and relationships in a document or among a set of documents, and can be used to select salient sentences. We present a temporal resolution algorithm, using focusing time and coreference chains, to convert Chinese temporal expressions in a document into calendrical forms. Moreover, we consider the last calendrical form of a sentence as a sentence time stamp to address sentence ordering. Informative words, event words, and temporal words are introduced to a sentence reduction algorithm, which deals with both length constraints and information coverage. Experiments on Chinese-news data sets show significant improvements of both information coverage and readability.
Keywords
Computer Science
A trainable document summarizer
1,349 Citations1995Julian Kupiec, Jan Pedersen +1 more
The trends in the results are in agreement with those of Edmundson who used a subjectively weighted combination of features as opposed to training the feature weights using a corpus, which suggests that even shorter extracts may be useful indicative summmies.
Generic text summarization using relevance measure and latent semantic analysis
847 Citations2001Yihong Gong, Xin Liu
This paper proposes two generic text summarization methods that create text summaries by ranking and extracting sentences from the original documents, and uses the latent semantic analysis technique to identify semantically important sentences, for summary creations.
Information fusion in the context of multi-document summarization
385 Citations1999Regina Barzilay, Kathleen McKeown +1 more
This approach is unique in its usage of language generation to reformulate the wording of the summary by identifying and synthesizing similar elements across related text from a set of multiple documents.
Robust temporal processing of news
358 Citations2000Inderjeet Mani, George D. Wilson
An annotation scheme for temporal expressions, and a method for resolving temporal expressions in print and broadcast news, based on both hand-crafted and machine-learnt rules are described.
Journal of Artificial Intelligence ResearchInferring Strategies for Sentence Ordering in Multidocument News Summarization
333 Citations2002Regina Barzilay, Noémie Elhadad
A strategy for ordering information that combines constraints from chronological order of events and topical relatedness is implemented and Evaluation of the augmented algorithm shows a significant improvement of the ordering over two baseline strategies.
Identifying topics by position
269 Citations1997Chin-Yew Lin, Eduard Hovy
The automated training and evaluation of an Optimal Position Policy is described, a method of locating the likely positions of topic-bearing sentences based on genre-specific regularities of discourse structure that can be used in applications such as information retrieval, routing, and text summarization.
Probabilistic text structuring
265 Citations2003Mirella Lapata
An approach to information ordering that is particularly suited for text-to-text generation and the appropriateness of such a model for multidocument summarization is assessed.
Information Processing & ManagementText summarization using a trainable summarizer and latent semantic analysis
249 Citations2004Jen‐Yuan Yeh, Hao‐Ren Ke +2 more
One approach is a trainable summarizer, which takes into account several features, including position, positive keyword, negative keyword, centrality, and the resemblance to the title, to generate summaries, while the other uses latent semantic analysis (LSA) to derive the semantic matrix of a document or a corpus and uses semantic sentence representation to construct a semantic text relationship map.
From single to multi-document summarization
233 Citations2001Chin-Yew Lin, Eduard Hovy
NeATS is a multi-document summarization system that attempts to extract relevant or interesting portions from a set of documents about some topic and present them in coherent order.
Treebanks Building and Using Parsed Corpora
219 Citations2014Anne Abeillé
This chapter discusses treebanks in English, German, and Slavic languages, as well as an HPSG-annotated test suite for Polish and a Dependency-based evaluation of minipar Dekang Lin.
Automated Text Summarization
178 Citations2005Chin-Yew Lin
This tutorial will review the state of the art in automatic summarization, and will discuss and critically evaluate current approaches to the problem, including manual evaluation procedures used in DUC, the factoid and pyramid method reference summary creation procedures and fully automatic evaluation method such as ROUGE.
Columbia Academic Commons (Columbia University)Event-Based Extractive Summarization
157 Citations2004Elena Filatova, Vasileios Hatzivassiloglou
The experimental results indicate that not only the event-based features offer an improvement in summary quality over words as features, but that this effect is more pronounced for more sophisticated summarization methods that avoid redundancy in the output.
Experiments in Single and Multi-Document Summarization Using MEAD
153 Citations2001Dragomir Radev, Sasha Blair-Goldensohn +1 more
This paper describes four experiments in text summarization about the identification by human subjects of cross-document structural relationships such as identity, paraphrase, elaboration, and fulfillment and presents numerical evaluations of all four experiments.
A formal model for information selection in multi-sentence text extraction
108 Citations2004Elena Filatova, Vasileios Hatzivassiloglou
A formal model is proposed that represents a collection of documents in a two-dimensional space of textual and conceptual units with an associated mapping between these two dimensions and is used to describe the task of selecting textual units for a summary or answer as a formal optimization task.
Text Summarization Using Lexical Chains
62 Citations2001Meru Brunn, Yllias Chali +1 more
This paper presents the summarizer of the University of Lethbridge at DUC 2001, which is based on an efficient use of lexical chains.
A multilingual news summarizer
59 Citations2000Hsin‐Hsi Chen, Chuan‐Jie Lin
This paper proposes architecture of multilingual news summarizer, including monolingual and multilingual clustering, similarity measure among meaningful units, and presentation of summarization results.
Journal of the American Society for Information Science and TechnologyA summarization system for Chinese news from multiple sources
36 Citations2003Hsin‐Hsi Chen, June‐Jei Kuo +3 more
In large-scale experiments, the results show that those models using informative words outperform pure heuristic voting-only strategy by news reporters and can be easily further applied to summarize multilingual news from multiple sources.
Applying machine learning to Chinese temporal relation resolution
36 Citations2004Wenjie Li, Kam‐Fai Wong +2 more
A computational model based on machine learning and heterogeneous collaborative bootstrapping is proposed for analyzing temporal relations in a Chinese multiple-clause sentence, which takes into account the effects of linguistic features such as tense/aspect, temporal connectives, and discourse structures.
ACM SIGIR ForumText Summarization Challenge 2 text summarization evaluation at NTCIR workshop 3
36 Citations2004Manabu Okumura, Takahiro Fukusima +2 more
Event tracking based on domain dependency
29 Citations2000Fumiyo Fukumoto, Yoshimi Suzuki
The method for event tracking on broadcast news stories based on distinction between a topic and an event using a simple criterion called domain dependency of words: how greatly a word features a given set of data is proposed.
Lecture notes in computer scienceClustering and Visualization in a Multi-lingual Multi-document Summarization System
22 Citations2003Hsin‐Hsi Chen, June‐Jei Kuo +1 more
Five strategies to compute the multilingual sentence similarity are presented and the experimental results show that sentence alignment without considering the word position or order in a sentence obtains the best performance.
Information Processing & ManagementCross-document event clustering using knowledge mining from co-reference chains
15 Citations2006June‐Jei Kuo, Hsin‐Hsi Chen
A metric of normalized chain edit distance to mine, incrementally, controlled vocabulary from cross-document coreference chains is proposed to unify terms among different co-reference chains.
Text, speech and language technologySinica Treebank
14 Citations2003Keh-Jiann Chen, Chi-Ching Luo +5 more
NTCIRQuery-based Multidocument Summarization for Information Retrieval
11 Citations2004Toshihiko Sakurai, Akira Utsumi
This paper presents a genre-independent method of generating a single summary from a set of the retrieved documents for information retrieval, which generates the core part of the summary from the most relevant document to a query.
Columbia Academic Commons (Columbia University)Identifying similarities and differences across English and Arabic news
9 Citations2005Kathleen McKeown, David K. Evans
A new approach for summarizing topically clustered documents from two sources, En-glish and machine translated Arabic texts, that presents users with an overview of the differences in content of the two sources is presented, enabling analysts to more quickly understand differences between incoming documents from different sources.
Lecture notes in computer scienceCoherent Arrangement of Sentences Extracted from Multiple Newspaper Articles
7 Citations2004Naoaki Okazaki, Yutaka Matsuo +1 more
This work proposes a novel method to plan a coherent arrangement of sentences extracted from multiple newspaper articles and shows that sentence reordering has a discernible effect on summary readability.
An NTU-approach to automatic sentence extraction for summary generation
4 Citations1996Kuang‐Hua Chen, Shengjie Huang +2 more
This paper proposes two different models to extract sentences for summary generation under two tasks initiated by SUMMAC-1, and outperforms the average system in categorization task but does a common job in adhoc task.
Lecture notes in computer scienceSignificant Sentence Extraction by Euclidean Distance Based on Singular Value Decomposition
3 Citations2005Changbeom Lee, Hyuk-Ro Park +1 more
Experimental results on Korean newspaper articles show that the proposed method is to be preferred over random selection of sentences or only PCA when summarization is the goal.