Dependency-based sentence alignment for multiple document summarization

Authors:
Tsutomu Hirao;Jun Suzuki;Hideki Isozaki;Eisaku Maeda
Affiliations:
NTT Communication Science Laboratories, NTT Corp., Seika-cho, Soraku-gun, Kyoto, Japan;NTT Communication Science Laboratories, NTT Corp., Seika-cho, Soraku-gun, Kyoto, Japan;NTT Communication Science Laboratories, NTT Corp., Seika-cho, Soraku-gun, Kyoto, Japan;NTT Communication Science Laboratories, NTT Corp., Seika-cho, Soraku-gun, Kyoto, Japan
Venue:
COLING '04 Proceedings of the 20th international conference on Computational Linguistics
Year:
2004

Citing 10
Cited 11

The decomposition of human-written summary sentences

Proceedings of the 22nd annual international ACM SIGIR conference on Research and development in information retrieval
The automatic construction of large-scale corpora for summarization research

Proceedings of the 22nd annual international ACM SIGIR conference on Research and development in information retrieval
Text classification using string kernels

The Journal of Machine Learning Research
Word sequence kernels

The Journal of Machine Learning Research
TextTiling: segmenting text into multi-paragraph subtopic passages

Computational Linguistics
BLEU: a method for automatic evaluation of machine translation

ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
Hierarchical directed acyclic graph kernel: methods for structured natural language data

ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
Japanese dependency analysis using cascaded chunking

COLING-02 proceedings of the 6th conference on Natural language learning - Volume 20
Sentence alignment for monolingual comparable corpora

EMNLP '03 Proceedings of the 2003 conference on Empirical methods in natural language processing
Text summarization challenge 2: text summarization evaluation at NTCIR workshop 3

HLT-NAACL-DUC '03 Proceedings of the HLT-NAACL 03 on Text summarization workshop - Volume 5

Kernel-based approach for automatic evaluation of natural language generation technologies: application to automatic summarization

HLT '05 Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing
ParaMT: A Paraphraser for Machine Translation

PROPOR '08 Proceedings of the 8th international conference on Computational Processing of the Portuguese Language
A Graph-Based Approach for Sentiment Sentence Extraction

New Frontiers in Applied Data Mining
Selecting sentences for answering complex questions

EMNLP '08 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Complex question answering: unsupervised learning approaches and experiments

Journal of Artificial Intelligence Research
Sentence comparison using robust minimal recursion semantics and an ontology

LD '06 Proceedings of the Workshop on Linguistic Distances
Do automatic annotation techniques have any impact on supervised complex question answering?

ACLShort '09 Proceedings of the ACL-IJCNLP 2009 Conference Short Papers
Using semantic information to answer complex questions

Canadian AI'11 Proceedings of the 24th Canadian conference on Advances in artificial intelligence
Improving graph-based random walks for complex question answering using syntactic, shallow semantic and extended string subsequence kernels

Information Processing and Management: an International Journal
Query-focused multi-document summarization: Automatic data annotations and supervised learning approaches

Natural Language Engineering
Unsupervised modeling of dialog acts in asynchronous conversations

IJCAI'11 Proceedings of the Twenty-Second international joint conference on Artificial Intelligence - Volume Volume Three

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we describe a method of automatic sentence alignment for building extracts from abstracts in automatic summarization research. Our method is based on two steps. First, we introduce the "dependency tree path" (DTP). Next, we calculate the similarity between DTPs based on the ESK (Extended String Subsequence Kernel), which considers sequential patterns. By using these procedures, we can derive one-to-many or many-to-one correspondences among sentences. Experiments using different similarity measures show that DTP consistently improves the alignment accuracy and that ESK gives the best performance.