Semantic argument frequency-based multi-document summarization

Aksoy, Cem; Bugdayci, Ahmet; Gur, Tunay; Uysal, İbrahim; Can, Fazlı

doi:10.1109/iscis.2009.5291878

Cited by 17 publications

(14 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…By considering the within-document sentence relations and the crossdocument sentence relations as two separate modalities (graphs), it ranks the sentences and selects top ones. [Aksoy et al 2009]. This method makes use of the frequencies of semantic roles in the document set.…”

Section: Sen-mtlmentioning

confidence: 99%

Deep Dependency Substructure-Based Learning for Multidocument Summarization

Wan

2015

ACM Trans. Inf. Syst.

View full text Add to dashboard Cite

Most extractive style topic-focused multidocument summarization systems generate a summary by ranking textual units in multiple documents and extracting a proper subset of sentences biased to the given topic. Usually, the textual units are simply represented as sentences or n-grams, which do not carry deep syntactic and semantic information. This article presents a novel extractive topic-focused multidocument summarization framework. The framework proposes a new kind of more meaningful and informative units named frequent Deep Dependency Sub-Structure (DDSS) and a topic-sensitive Multi-Task Learning (MTL) model for frequent DDSS ranking. Given a document set, first, we parse all the sentences into deep dependency structures with a Head-driven Phrase Structure Grammar (HPSG) parser and mine the frequent DDSSs after semantic normalization. Then we employ a topic-sensitive MTL model to learn the importance of these frequent DDSSs. Finally, we exploit an Integer Linear Programming (ILP) formulation and use the frequent DDSSs as the essentials for summary extraction. Experimental results on two DUC datasets demonstrate that our proposed approach can achieve state-of-the-art performance. Both the DDSS information and the topic-sensitive MTL model are validated to be very helpful for topic-focused multidocument summarization. ACM Reference Format:Su Yan and Xiaojun Wan. 2015. Deep dependency substructure-based learning for multidocument summarization.

show abstract

Section: Sen-mtlmentioning

confidence: 99%

Deep Dependency Substructure-Based Learning for Multidocument Summarization

Wan

2015

ACM Trans. Inf. Syst.

View full text Add to dashboard Cite

show abstract

“…Aksoy et al [38] simply score sentences according to their inclusion of frequent semantic phrases. Wang et al [22] use the semantic role information as constraints for word matching when calculating sentence similarity.…”

Section: Related Workmentioning

confidence: 99%

“…Then the Random-Walk algorithm is applied to rank sentences. SRL-Freq [38] This method makes use of the frequencies of semantic roles in the document set. It calculates the score of a sentence by summing up its similarity to the semantic roles in the document set, and the top scoring sentences are selected one-by-one into the summary.…”

Section: B Baselinementioning

confidence: 99%

SRRank: Leveraging Semantic Roles for Extractive Multi-Document Summarization

Wan

2014

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

Extractive multi-document summarization systems usually rank sentences in a document set with some ranking strategy and then select a few highly ranked sentences into the summary. One of the most popular ranking algorithms is the graph-based ranking algorithm. In this paper, we investigate making use of semantic role information to enhance the graph-based ranking algorithm for multi-document summarization. We first parse the sentences and obtain the semantic roles, and then propose a novel SRRank algorithm and two extensions to make better use of the semantic role information. Our proposed algorithms can simultaneously rank the sentences, semantic roles and words in a heterogeneous ranking process. Experimental results on two DUC datasets demonstrate that our proposed algorithms significantly outperform a few baselines, and the semantic role information is validated to be very helpful for multi-document summarization.Index Terms-Graph-based ranking algorithm, multi-document summarization, semantic roles.

show abstract

“…This approach can be used when the source documents have event chronology information. Another approach used by Aksoy et al calculates the relative position of each sentence to the original document, assuming that each document has the same flow of information [9]. The position of each sentence is calculated using a ratio of sentence length to the length of its original document.…”

Section: A Extractive Summarizationmentioning

confidence: 99%

Improving coherence by reordering the output of extractive summarization using Centering Theory through genetic algorithm

Yuliawati

Manurung

2013

2013 International Conference on Advanced Computer Science and Information Systems (ICACSIS)

View full text Add to dashboard Cite

Extractive summarization is a widely studied and fairly easy to implement technique. It works by choosing the most important parts of a document(s) as a summary. However, this can lead to a lack of coherence in the summary itself. In this study, the principle of continuity in Centering Theory is used to maintain the entity coherence between subsequent sentences obtained from extractive news summarizer. Simultaneously, the relative order of sentences belonging to the same source document is maintained. These two considerations are implemented as fitness functions for a genetic algorithm that is used to obtain the optimal ordering of sentences in the summary. Based on the results of our study involving human judgment, a weighted fitness function combining 75% continuity and 25% relative order yields the most acceptable sentence ordering.

show abstract

Semantic argument frequency-based multi-document summarization

Cited by 17 publications

References 17 publications

Deep Dependency Substructure-Based Learning for Multidocument Summarization

Deep Dependency Substructure-Based Learning for Multidocument Summarization

SRRank: Leveraging Semantic Roles for Extractive Multi-Document Summarization

Improving coherence by reordering the output of extractive summarization using Centering Theory through genetic algorithm

Contact Info

Product

Resources

About