A prototype system for multilingual data discovery of International Long-Term Ecological Research (ILTER) Network data

Vanderbilt, Kristin; Porter, John H.; Lu, Sheng-Shan; Bertrand, Nic; Blankman, David; Guo, Xiaoqing; He, Honglin; Henshaw, Don; Jeong, Karpjoo; Kim, Eun-Shik; Lin, Chau-Chin; O'Brien, Margaret; Osawa, Takeshi; Tuama, Éamonn Ó; Su, Wen; Yang, Hai‐Bo

doi:10.1016/j.ecoinf.2016.11.011

Cited by 6 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Language and translation have also been issues (Vanderbilt et al . ). All approaches must assess knowledge gaps, data gaps, and data representativeness, but should also determine the feasibility and need for a new network.…”

Section: Design Principles For Seosmentioning

confidence: 97%

“…ILTER collaboration is usually conducted through workshop series. Examples of such work include: analysis of ecosystem services (eg Shibata and Bourgeron 2011;Vihervaara et al 2013;Maass et al 2016); nitrogen cycles (eg Shibata et al 2015); and data sharing (eg Vanderbilt et al 2015Vanderbilt et al , 2017. The main weakness of the network is the lack of core funding and the voluntary basis of membership dues.…”

Section: Panel 1 the International Long Term Ecological Research Netmentioning

confidence: 99%

“…In an international context, challenges to data sharing include unequal distribution among networks of information management expertise, user-friendly tools, and resources (Vanderbilt et al 2015). Language and translation have also been issues (Vanderbilt et al 2017). All approaches must assess knowledge gaps, data gaps, and data representativeness, but should also determine the feasibility and need for a new network.…”

Section: P Bourgeron Et Almentioning

confidence: 99%

See 2 more Smart Citations

Understanding large‐scale, complex, human–environmental processes: a framework for social–ecological observatories

Bourgeron

Kliskey

Alessa

et al. 2018

Frontiers in Ecol & Environ

View full text Add to dashboard Cite

There is a growing consensus that transdisciplinary environmental networks are required to generate knowledge of the dynamics of coupled human–natural systems (CHANs) and to assess societal and policy consequences of complex environmental issues. Few of the existing large environmental observatory networks collect much, if any, data on the CHANs coupling mechanisms, reaffirming the need to develop observing approaches and structures that address the interoperability of the diverse data being obtained from these systems. We review the characteristics of existing environmental observatories and similar initiatives used to monitor CHANs, and identify opportunities for interoperability among them. From a synthesis of the characteristics of environmental networks representing a wide spectrum of research approaches and applications, a conceptual framework of a typical Social–Ecological Observatory (SEO) is presented to support long‐term, multi‐scaled CHANs observations through a common set of principles for organizing the observatories. Finally, we identify three areas of emphasis where progress is needed to support the use and application of SEOs.

show abstract

Section: Design Principles For Seosmentioning

confidence: 97%

Section: Panel 1 the International Long Term Ecological Research Netmentioning

confidence: 99%

Section: P Bourgeron Et Almentioning

confidence: 99%

See 1 more Smart Citation

Understanding large‐scale, complex, human–environmental processes: a framework for social–ecological observatories

Bourgeron

Kliskey

Alessa

et al. 2018

Frontiers in Ecol & Environ

View full text Add to dashboard Cite

show abstract

“…Ontology-based query expansion is mainly used in subject-specific dataset retrieval. For example, Dulisch et al (2015) used the Thesaurus for Social Sciences to expand queries in Social Science; Wright et al (2017) proposed using the Medical Subject Heading to expand queries, which led to 1.2% and 1.3% improvement in NDCG@10 and P@10 respectively; Vanderbilt et al (2017) used the multilingual EnvThes to expand queries in Ecology to improve dataset retrieval performance. As developing ontology is costly and ontologies of high quality are limited, this method mainly applies to the retrieval of datasets from specific subject areas.…”

Section: Sparse Retrieval Modelmentioning

confidence: 99%

Learning Domain‐specific Semantic Representation from Weakly Supervised Data to Improve Research Dataset Retrieval

Luo

Hong

Wang

et al. 2022

Proceedings of the Association for Information Science and Tech

View full text Add to dashboard Cite

Along with the development of the data‐driven research paradigm, there are exponentially increasing datasets, which bring challenges to researchers in the efficient retrieval of relevant datasets. Previous studies mainly focused on query expansion methods based on sparse retrieval models to improve the accuracy and recall in retrieval. We investigated the use of semantically rich information to retrieve relevant datasets and the benefits of using domain‐specific dense vector representation as opposed to general representation. First, we used pairs of metadata fields that have semantic relevance to construct the domain‐specific weakly supervised training data. Then, a pre‐trained transformer‐based deep learning model is fine‐tuned on the training data using the contrastive learning method. Finally, dense vector representations of the queries and datasets are obtained based on the fine‐tuned model. The relevance of a dataset to a query is measured by the similarity between the vectors. To evaluate the performance of the proposed model, we collected 104,683 datasets from 13 research data repositories, recruited volunteers to design research‐oriented queries, and annotated the retrieval results. The experimental results show that compared with the domain‐independent fine‐tuned model, our proposed method can improve the NDCG@10 score by about 5%.

show abstract

A Retrospective of Information Management in the Long Term Ecological Research Program

Stafford

2021

Archimedes

View full text Add to dashboard Cite

A prototype system for multilingual data discovery of International Long-Term Ecological Research (ILTER) Network data

Cited by 6 publications

References 17 publications

Understanding large‐scale, complex, human–environmental processes: a framework for social–ecological observatories

Understanding large‐scale, complex, human–environmental processes: a framework for social–ecological observatories

Learning Domain‐specific Semantic Representation from Weakly Supervised Data to Improve Research Dataset Retrieval

A Retrospective of Information Management in the Long Term Ecological Research Program

Contact Info

Product

Resources

About