Filters








10,800 Hits in 1.5 sec

Multi-Vector Models with Textual Guidance for Fine-Grained Scientific Document Similarity [article]

Sheshera Mysore, Arman Cohan, Tom Hope
2022 arXiv   pre-print
We present a new scientific document similarity model based on matching fine-grained aspects of texts.  ...  Further, our fast single-match method achieves competitive results, paving the way for applying fine-grained similarity to large scientific corpora.  ...  Conclusions We presented ASPIRE, a scientific document similarity model that is trained by leveraging co-citation contexts for learning fine-grained similarity.  ... 
arXiv:2111.08366v3 fatcat:zltoorxljvbk5e2h3epvpv3kou

Scientific Literature Summarization using Document Structure and Hierarchical Attention Model

Huiyan Xu, Zhijian Wang, Xiaolan Weng
2019 IEEE Access  
of scientific literature, therefore, we employ a hierarchical attention model to learn document structure from all the papers for summarization.  ...  Since the structure of documents is very important for scientific literature summarization, and it is obviously observed that there is a relationship and semantic information hidden in document structures  ...  Cohan and Goharian [12] integrate citations and citation contexts to summarize for a scientific document.  ... 
doi:10.1109/access.2019.2960611 fatcat:436ftv5ggze7zn6j64dbjjlwoq

Ranking by inspiration: a network science approach

Livio Bioglio, Valentina Rho, Ruggero G. Pensa
2019 Machine Learning  
In fact, in scientific citation networks, influential topics are usually considered those ones that spread most rapidly in the network.  ...  In bibliographic networks, for instance, an information diffusion process takes place when some authors, that publish papers in a given topic, influence some of their neighbors (coauthors, citing authors  ...  Igor Pesando for his support in interpreting the results on the high energy physics dataset.  ... 
doi:10.1007/s10994-019-05828-9 fatcat:ihpsmo3hdfh5phl63cxjsjr5ku

Bibliometric impact measures leveraging topic analysis

Gideon S. Mann, David Mimno, Andrew McCallum
2006 Proceedings of the 6th ACM/IEEE-CS joint conference on Digital libraries - JCDL '06  
Recent developments in latent topic models have produced promising results for automatic sub-field discovery.  ...  citation indexing system.  ...  This paper explores new possibilities for impact measures in scientometrics by leveraging topic models.  ... 
doi:10.1145/1141753.1141765 dblp:conf/jcdl/MannMM06 fatcat:z6ygghtkknfpzflazsuqi7co4i

Scientific Article Summarization Using Citation-Context and Article's Discourse Structure

Arman Cohan, Nazli Goharian
2015 Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing  
We propose a summarization approach for scientific articles which takes advantage of citation-context and the document discourse model.  ...  We also leverage the inherent scientific article's discourse for producing better summaries.  ...  Acknowledgments The authors would like to thank the three anonymous reviewers for their valuable feedback and comments.  ... 
doi:10.18653/v1/d15-1045 dblp:conf/emnlp/CohanG15 fatcat:27e6daoag5frfaf4kydazpkhgi

A Micro Perspective of Research Dynamics Through "Citations of Citations" Topic Analysis

Xiaoli Chen, Tao Han
2020 Journal of Data and Information Science  
highly cited work, scientific influence exists in indirect citations.  ...  Topic modeling can reveal how long this influence exists in forward chaining, as well as its influence.Research limitationsThis paper measures scientific influence and indirect scientific influence only  ...  Acknowledgement This work is supported by the Programs for the Young Talents of National Science Library, Chinese Academy of Sciences (Grant No. 2019QNGR003).  ... 
doi:10.2478/jdis-2020-0034 fatcat:jf6hkvykfba2hdu26oba3o3u3e

New Trends in Scientific Knowledge Graphs and Research Impact Assessment

Paolo Manghi, Andrea Mannocci, Francesco Osborne, Dimitris Sacharidis, Angelo Salatino, Thanasis Vergoulis
2021 Quantitative Science Studies  
We also would like to thank Professor Ludo Waltman for welcoming this special issue to the Quantitative Science Studies Journal and for his excellent guidance throughout the whole process.  ...  Last but not least, we are grateful to the Technische Informationsbibliothek (TIB)-Leibniz Information Centre for Science and Technology for partially covering the APCs of the papers published in this  ...  Stateof-the-art methods for this problem attempt to leverage the current citation data of each paper.  ... 
doi:10.1162/qss_e_00160 fatcat:rm24dfhm5nf6xnhybgchbd2za4

Scientific Article Summarization Using Citation-Context and Article's Discourse Structure [article]

Arman Cohan, Nazli Goharian
2017 arXiv   pre-print
We propose a summarization approach for scientific articles which takes advantage of citation-context and the document discourse model.  ...  We also leverage the inherent scientific article's discourse for producing better summaries.  ...  Acknowledgments The authors would like to thank the three anonymous reviewers for their valuable feedback and comments.  ... 
arXiv:1704.06619v1 fatcat:mxma4qah3vhoncy6nz2av6an7m

Follow the Leader: Documents on the Leading Edge of Semantic Change Get More Citations [article]

Sandeep Soni, Kristina Lerman, Jacob Eisenstein
2020 arXiv   pre-print
Our work thus provides a new technique for identifying lexical semantic leaders and demonstrates a new link between progressive use of language and influence in a citation network.  ...  We analyze two large collections of documents, representing legal opinions and scientific articles.  ...  Citation impact The number of citations a document receives has long been used as a proxy for the impact and influence of scientific articles [Fortunato et al., 2018] , legal opinions [Fowler et al.,  ... 
arXiv:1909.04189v2 fatcat:fvn3buftzrf3zplulqcjxweeia

Mapping Complex Technologies via Science-Technology Linkages; The Case of Neuroscience – A transformer based keyword extraction approach [article]

Daniel Hain, Roman Jurowetzki, Mariagrazia Squicciarini
2022 arXiv   pre-print
Specifically, we utilize transformer based language models, tailored for use with scientific text, to detect coherent topics over time and describe these by relevant keywords that are automatically extracted  ...  We are able to map technologies identified in scientific literature to patent applications, thereby providing an empirical foundation for the study of science-technology linkages.  ...  (Cohan et al., 2020) , a state of the art transformer language model for document-level embedding for scientific text.  ... 
arXiv:2205.10153v1 fatcat:35l4xzj4vzennhmq4qjsoxilru

Detecting topic evolution in scientific literature

Qi He, Bi Chen, Jian Pei, Baojun Qiu, Prasenjit Mitra, Lee Giles
2009 Proceeding of the 18th ACM conference on Information and knowledge management - CIKM '09  
However, the impact of one document on another as captured by citations, one important inherent element in scientific literature, has not been considered.  ...  In this paper, we address the problem of understanding topic evolution by leveraging citations, and develop citation-aware approaches.  ...  In this paper, we tackle the problem of topic evolution analysis on scientific literature by leveraging citations.  ... 
doi:10.1145/1645953.1646076 dblp:conf/cikm/HeCPQMG09 fatcat:o2zrbdp4k5dtdgojabwnkem6jm

Enhancing Scientific Papers Summarization with Citation Graph [article]

Chenxin An, Ming Zhong, Yiran Chen, Danqing Wang, Xipeng Qiu, Xuanjing Huang
2021 arXiv   pre-print
Previous work for text summarization in scientific domain mainly focused on the content of the input document, but seldom considering its citation network.  ...  However, scientific papers are full of uncommon domain-specific terms, making it almost impossible for the model to understand its true meaning without the help of the relevant research community.  ...  Acknowledgements We would like to thank the anonymous reviewers for their valuable suggestions.  ... 
arXiv:2104.03057v1 fatcat:ytexhltfnbfcjg2om33maggpgu

Understanding evolution of research themes

Xiaolong Wang, Chengxiang Zhai, Dan Roth
2013 Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining - KDD '13  
The key idea is to represent a research paper by a "bag of citations" and model such a "citation document" with a probabilistic topic model.  ...  We explore the extension of a particular topic model, i.e., Latent Dirichlet Allocation (LDA), for citation analysis, and show that such a Citation-LDA can facilitate discovering of individual research  ...  Government is authorized to reproduce and distribute reprints for Governmental purposes notwithstanding any copyright annotation thereon.  ... 
doi:10.1145/2487575.2487698 dblp:conf/kdd/WangZR13 fatcat:hjttatvqk5bgzowb4msvcewnlq

Mining Scholarly Communication and Interaction on the Social Web

Asmelash Teka Hadgu
2015 Proceedings of the 24th International Conference on World Wide Web - WWW '15 Companion  
As a result, there is a need for a comprehensive approach to gain a broader understanding and timely signals of scientific communication as well as how researchers interact on the social web.  ...  Applying reproducible research, contributing applications and data sets, the thesis proposal strives to add value by mining the social web for social good.  ...  We can model the user-to-user relationship among researchers, leveraging their academic relationships such as the co-authorship, citation network and their affiliation besides the Twitter generated interactions  ... 
doi:10.1145/2740908.2741749 dblp:conf/www/Hadgu15 fatcat:ylwbhl3ipzacnli4pon5bw2xny

The impact of peer review on the contribution potential of scientific papers

Akira Matsui, Emily Chen, Yunwen Wang, Emilio Ferrara
2021 PeerJ  
Using sentiment analysis, Latent Dirichlet Allocation (LDA) topic modeling, mixed linear regression models, and logit regression models, we examine how the peer-reviewing process influences the acceptance  ...  This study leverages open data from nearly 5,000 PeerJ publications that were eventually accepted.  ...  Selection of the number of topics for LDA topic modeling We utilize the perplexity and coherence scores to determine an appropriate number of topics for LDA to use as a hyperparameter.  ... 
doi:10.7717/peerj.11999 pmid:34616596 pmcid:PMC8459734 fatcat:s5qc3qgrpvbunaibfnw4pzxpvi
« Previous Showing results 1 — 15 out of 10,800 results