Cross-media Event Extraction and Recommendation

Lu, Di; Voss, Clare R.; Tao, Fangbo; Ren, Xiang; Guan, Rachel; Korolov, Rostyslav; Zhang, Tongtao; Wang, Dongang; Zhang, Lipeng; Cassidy, Taylor; Ji, Heng; Chang, Shih‐Fu; Wallace, William A.; Hendler, James A.; Si, Mei; Kaplan, Lance

doi:10.18653/v1/n16-3015

Cited by 9 publications

(6 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They could be used to index the events describing the elements, such as "what", "how" and "why". The event space model could be used to recommend information resources in clusters related to the specified events (Lu et al, 2016) and scientific information analysis (Zhang et al, 2016).…”

Section: Discussionmentioning

confidence: 99%

Semantically linking events for massive scientific literature research

Zhang

Sun

Yao

2017

View full text Add to dashboard Cite

Purpose This paper aims to semantically linking scientific research events implied by scientific and technical literature to support information analysis and information service applications. Literature research is an important method to acquire scientific and technical information which is important for research, development and innovation of science and technology. It is difficult but urgently required to acquire accurate, timely, rapid, short and comprehensive information from the large-scale and fast-growing literature, especially in the big data era. Existing literature-based information retrieval systems focus on basic data organization, and they are far from meeting the needs of information analytics. It becomes urgent to organize and analyze scientific research events related to scientific and technical literature for forecasting development trend of science and technology. Design/methodology/approach Scientific literature such as a paper or a patent is represented as a scientific research event, which contains elements including when, where, who, what, how and why. Metadata of literature is used to formulate scientific research events that are implied in introduction and related work sections of literature. Named entities and research objects such as methods, materials and algorithms can be extracted from texts of literature by using text analysis. The authors semantically link scientific research events, entities and objects, and then, they construct the event space for supporting scientific and technical information analysis. Findings This paper represents scientific literature as events, which are coarse-grained units comparing with entities and relations in current information organizations. Events and semantic relations among them together formulate a semantic link network, which could support event-centric information browsing, search and recommendation. Research limitations/implications The proposed model is a theoretical model, and it needs to verify the efficiency in further experimental application research. The evaluation and applications of semantic link network of scientific research events are further research issues. Originality/value This paper regards scientific literature as scientific research events and proposes an approach to semantically link events into a network with multiple-typed entities and relations. According to the needs of scientific and technical information analysis, scientific research events are organized into event cubes which are distributed in a three-dimensioned space for easy-to-understand and information visualization.

show abstract

Section: Discussionmentioning

confidence: 99%

Semantically linking events for massive scientific literature research

Zhang

Sun

Yao

2017

View full text Add to dashboard Cite

show abstract

“…In the future, we plan to generalize the stream summarization problem to various streams such as social (e.g., Twitter), image (e.g., Imgur) and even video streams (e.g., Youtube), which would yield many interesting and practical applications (Lu et al, 2016) to deal with the information overload challenge in the big data era.…”

Section: Discussionmentioning

confidence: 99%

News Stream Summarization using Burst Information Networks

Ge¹,

Cui²,

Chang³

et al. 2016

Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

This paper studies summarizing key information from news streams. We propose simple yet effective models to solve the problem based on a novel and promising representation of text streams-Burst Information Networks (BINets). A BINet can be aware of redundant information, allows global analysis of a text stream, and can be efficiently built and dynamically updated, which perfectly fits the demands of text stream summarization. Extensive experiments show that the BINet-based approaches are not only efficient and can be used in a real-time online summarization setting, but also can generate high-quality summaries, outperforming the state-of-the-art approach.

show abstract

“…The identification and summarization of events for the recommendations according to the user browsing interest incorporated a medium-level human agency. 61 EE techniques help to improve the efficiency and accuracy of IE from the text, but still, the research is at the infancy stage. Unstructured big data add tremendous challenges to this research due to multimodality, heterogeneity, and complexity of data.…”

Section: Ie For Unstructured Data Analysismentioning

confidence: 99%

Limitations of information extraction methods and techniques for heterogeneous unstructured big data

Adnan

Akbar

2019

International Journal of Engineering Business Management

View full text Add to dashboard Cite

During the recent era of big data, a huge volume of unstructured data are being produced in various forms of audio, video, images, text, and animation. Effective use of these unstructured big data is a laborious and tedious task. Information extraction (IE) systems help to extract useful information from this large variety of unstructured data. Several techniques and methods have been presented for IE from unstructured data. However, numerous studies conducted on IE from a variety of unstructured data are limited to single data types such as text, image, audio, or video. This article reviews the existing IE techniques along with its subtasks, limitations, and challenges for the variety of unstructured data highlighting the impact of unstructured big data on IE techniques. To the best of our knowledge, there is no comprehensive study conducted to investigate the limitations of existing IE techniques for the variety of unstructured big data. The objective of the structured review presented in this article is twofold. First, it presents the overview of IE techniques from a variety of unstructured data such as text, image, audio, and video at one platform. Second, it investigates the limitations of these existing IE techniques due to the heterogeneity, dimensionality, and volume of unstructured big data. The review finds that advanced techniques for IE, particularly for multifaceted unstructured big data sets, are the utmost requirement of the organizations to manage big data and derive strategic information. Further, potential solutions are also presented to improve the unstructured big data IE systems for future research. These solutions will help to increase the efficiency and effectiveness of the data analytics process in terms of context-aware analytics systems, data-driven decision-making, and knowledge management.

show abstract

Cross-media Event Extraction and Recommendation

Cited by 9 publications

References 10 publications

Semantically linking events for massive scientific literature research

Semantically linking events for massive scientific literature research

News Stream Summarization using Burst Information Networks

Limitations of information extraction methods and techniques for heterogeneous unstructured big data

Contact Info

Product

Resources

About