Query-oriented unsupervised multi-document summarization via deep learning model

Zhong, Sheng-hua; Liu, Yanping; Li, Bin; Long, Jing

doi:10.1016/j.eswa.2015.05.034

Cited by 68 publications

(19 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3) Deep learning methods have already been applied to different multimedia applications successfully, especially after the introduction of DBN, such as audio event classification [10], document summarization [11], and image classification [12]. Following works provide support to the effectiveness and efficiency of deep learning methods from aspects of neuroscience, machine learning theory, and experimental results on real-world data.…”

Section: Methodsmentioning

confidence: 97%

Is noise always harmful? Visual learning from weakly-related data

Zhong

Liu

Hua

et al. 2015

2015 International Conference on Orange Technologies (ICOT)

Self Cite

View full text Add to dashboard Cite

Noise exists universally in multimedia data, especially in Internet era. For example, tags from web users are often incomplete, arbitrary, and low relevant with the visual information. Intuitively, noise in the dataset is harmful to learning tasks, which implies that huge volumes of image tags from social media can't be utilized directly. To collect the reliable training dataset, labor-intensive manual labeling and various learning based outlier detection techniques are widely used. This paper intends to discuss whether such kind of preprocessing is always needed. We focus on a very normal case in image classification that the available dataset includes a large amount of images weakly related to any target classes. We use deep models as the platform and design a series of experiments to compare the semi-supervised learning performance with/without weakly related unlabeled data. Fortunately, we validate that weakly related data is not always harmful, which is an encouraging finding for research on web image learning.

show abstract

Section: Methodsmentioning

confidence: 97%

Is noise always harmful? Visual learning from weakly-related data

Zhong

Liu

Hua

et al. 2015

2015 International Conference on Orange Technologies (ICOT)

Self Cite

View full text Add to dashboard Cite

show abstract

“…This line of research has received much attention in the past [4,12,14,16,18,21,31]. It was also investigated at the Document Understanding (DUC) and Text Analysis Conferences (TAC).…”

Section: Related Workmentioning

confidence: 98%

“…Traditional multi-document extractive summarization tasks [4,12,14,16,18,21,31] focus on generating textual summaries from filtered relevant documents such that they are as close as possible to a manually created summary. Unsupervised methods in this realm, consider only text to maximize relevance and reduce redundancy in the generated summaries.…”

Section: Event Querymentioning

confidence: 99%

See 1 more Smart Citation

Event Digest

Mishra

Berberich

2016

Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval

View full text Add to dashboard Cite

For a general user, easy access to vast amounts of online information available on past events has made retrospection much harder. We propose a problem of automatic event digest generation to aid effective and efficient retrospection. For this, in addition to text, a digest should maximize the reportage of time, geolocations, and entities to present a holistic view on the past event of interest.We propose a novel divergence-based framework that selects excerpts from an initial set of pseudo-relevant documents, such that the overall relevance is maximized, while avoiding redundancy in text, time, geolocations, and named entities, by treating them as independent dimensions of an event. Our method formulates the problem as an Integer Linear Program (ILP) for global inference to diversify across the event dimensions. Relevance and redundancy measures are defined based on JS-divergence between independent query and excerpt models estimated for each event dimension. Elaborate experiments on three real-world datasets are conducted to compare our methods against the state-of-the-art from the literature. Using Wikipedia articles as gold standard summaries in our evaluation, we find that the most holistic digest of an event is generated with our method that integrates all event dimensions. We compare all methods using standard Rouge-1, -2, and -SU4 along with Rouge-NP, and a novel weighted variant of Rouge.

show abstract

“…Finally, deep learning has been recently introduced to text summarization. Zhong et al [26] and Yousefi-Azar and Hamey [27] used different deep learning models with query-oriented single document and multi-document summarization, respectively.…”

Section: Machine Learning Approachesmentioning

confidence: 99%

Solving Multi-Document Summarization as an Orienteering Problem

Al-Saleh

Menaï

2018

Algorithms

View full text Add to dashboard Cite

With advances in information technology, people face the problem of dealing with tremendous amounts of information and need ways to save time and effort by summarizing the most important and relevant information. Thus, automatic text summarization has become necessary to reduce the information overload. This article proposes a novel extractive graph-based approach to solve the multi-document summarization (MDS) problem. To optimize the coverage of information in the output summary, the problem is formulated as an orienteering problem and heuristically solved by an ant colony system algorithm. The performance of the implemented system (MDS-OP) was evaluated on DUC 2004 (Task 2) and MultiLing 2015 (MMS task) benchmark corpora using several ROUGE metrics, as well as other methods. Its comparison with the performances of 26 systems shows that MDS-OP achieved the best F-measure scores on both tasks in terms of ROUGE-1 and ROUGE-L (DUC 2004), ROUGE-SU4, and three other evaluation methods (MultiLing 2015). Overall, MDS-OP ranked among the best 3 systems.

show abstract

Query-oriented unsupervised multi-document summarization via deep learning model

Cited by 68 publications

References 21 publications

Is noise always harmful? Visual learning from weakly-related data

Is noise always harmful? Visual learning from weakly-related data

Event Digest

Solving Multi-Document Summarization as an Orienteering Problem

Contact Info

Product

Resources

About