Filters








135 Hits in 5.8 sec

A Personalized Concept-driven Recommender System for Scientific Libraries

D. De Nart, C. Tasso
2014 Procedia Computer Science  
In this paper we consider the domain of scientific publications repositories and propose a content-based recommender based upon a graph representation of concepts built up by linked keyphrases.  ...  This recommender is coupled with a keyphrase extraction system able to generate meaningful metadata for the documents, which are the basis for providing helpful and explainable recommendations.  ...  More specifically, concepts are identified as keyphrases automatically extracted from scientific papers.  ... 
doi:10.1016/j.procs.2014.10.015 fatcat:uldbtbo7gfaj3m2t7266ovqkia

Creation and evaluation of large keyphrase extraction collections with multiple opinions

Lucas Sterckx, Thomas Demeester, Johannes Deleu, Chris Develder
2017 Language Resources and Evaluation  
While several Automatic Keyphrase Extraction (AKE) techniques have been developed and analyzed, there is little consensus on the definition of the task and a lack of overview of the effectiveness of different  ...  systematically evaluate keyphrase extraction using several supervised and unsupervised AKE techniques, (iii) and experimentally analyze the effects of disagreement on AKE evaluation.  ...  Acknowledgements The research presented in this article relates to STEAMER (http://www.iminds. be/en/projects/2014/07/12/steamer), a MiX-ICON project facilitated by iMinds Media and funded by IWT (now  ... 
doi:10.1007/s10579-017-9395-6 fatcat:4ylkgeswhzaevof2rbtdcy2d3i

A Distributed Framework for NLP-Based Keyword and Keyphrase Extraction From Web Pages and Documents

Paolo Nesi, Gianni Pantaleo, Gianmarco Sanesi
2015 Proceedings of the 21st International Conference on Distributed Multimedia Systems  
In order to automatically ingest and process such huge amounts of data, single-machine, non-distributed architectures are proving to be inefficient for tasks like Big Data mining and intensive text processing  ...  This has been achieved by integrating the APIs of the widespread GATE open source NLP platform in a multi-node cluster, built upon the open source Apache Hadoop file system.  ...  RELATED WORK The task of Automatic keyword extraction has been extensively studied in literature.  ... 
doi:10.18293/dms2015-024 dblp:conf/dms/NesiPS15 fatcat:ieenhxagojenfdivup23wt42h4

Automatic tag recommendation for metadata annotation using probabilistic topic modeling

Suppawong Tuarob, Line C. Pouchard, C. Lee Giles
2013 Proceedings of the 13th ACM/IEEE-CS joint conference on Digital libraries - JCDL '13  
ONE-Mercury harvests metadata from the data hosted by multiple repositories and makes it searchable.  ...  We transform the problem into a tag recommendation problem with a controlled tag library, and propose two variants of an algorithm for recommending tags.  ...  Two features are extracted from each candidate keyphrase: TF-IDF score and distance of the first occurrence of the keyphrase from the beginning of the document.  ... 
doi:10.1145/2467696.2467706 dblp:conf/jcdl/TuarobPG13 fatcat:trqnnkvi5baunjmx3dh3ohdmyu

A generalized topic modeling approach for automatic document annotation

Suppawong Tuarob, Line C. Pouchard, Prasenjit Mitra, C. Lee Giles
2015 International Journal on Digital Libraries  
The problem is first transformed into the tag recommendation problem with a controlled tag library. Then, two variants of an algorithm for automatic tag recommendation are presented.  ...  ONEMercury harvests metadata records from multiple archives and repositories, and makes them searchable.  ...  Acknowledgments We gratefully acknowledge useful comments from Natasha Noy, Jeffery S. Horsburgh, and Giri Palanisamy.  ... 
doi:10.1007/s00799-015-0146-2 fatcat:x6ynzrpumvag3jdrakegjvtyay

Is More Always Better? The Effects of Personal Characteristics and Level of Detail on the Perception of Explanations in a Recommender System

Mohamed Amine Chatti, Mouadh Guesmi, Laura Vorgerd, Thao Ngo, Shoeb Joarder, Qurat Ul Ain, Arham Muslim
2022 Proceedings of the 30th ACM Conference on User Modeling, Adaptation and Personalization  
To fill this research gap, we aim in this paper at a shift from a one-size-fits-all to a personalized approach to explainable recommendation by giving users agency in deciding which explanation they would  ...  We developed a transparent Recommendation and Interest Modeling Application (RIMA) that provides on-demand personalized explanations of the recommendations, with three levels of detail (basic, intermediate  ...  CONCLUSION AND FUTURE WORK In this paper, we aimed to shed light on an aspect that remains under-researched in the literature on explainable recommendation, namely the effects of personal characteristics  ... 
doi:10.1145/3503252.3531304 fatcat:kvmubwnpjzg7hfq4elpbjqplxe

Diverse Keyphrase Generation with Neural Unlikelihood Training [article]

Hareesh Bahuleyan, Layla El Asri
2020 arXiv   pre-print
We first analyze the extent of information redundancy present in the outputs generated by a baseline model trained using maximum likelihood estimation (MLE).  ...  In this paper, we study sequence-to-sequence (S2S) keyphrase generation models from the perspective of diversity.  ...  Acknowledgements We thank Francis Duplessis, Ivan Kobyzev, Jackie Chi Kit Cheung, Kushal Arora, Marjan Albooyeh, Mehran Kazemi, Simon Prince and Wenjie Zi for valuable inputs and helpful discussions.  ... 
arXiv:2010.07665v1 fatcat:kwwttfgxdbgx7nnuazqhkhhtky

BASIL: Effective Near-Duplicate Image Detection Using Gene Sequence Alignment [chapter]

Hung-sik Kim, Hau-Wen Chang, Jeongkyu Lee, Dongwon Lee
2010 Lecture Notes in Computer Science  
We also propose a heuristics-based method to extract n-gram keyphrases from noisy textual content by taking the importance of sub-term keywords into consideration. iii  ...  By taking various relationships into consideration, the data sparseness problem common in recommendation tasks are alleviated.  ...  [69] take advantage of the syntactic structure of a sentence to extract the keyphrases in a scientific articles.  ... 
doi:10.1007/978-3-642-12275-0_22 fatcat:ou4wo4a6efdabkipzbkaxd5cyi

From keywords to keyqueries

Tim Gollub, Matthias Hagen, Maximilian Michel, Benno Stein
2013 Proceedings of the 36th international ACM SIGIR conference on Research and development in information retrieval - SIGIR '13  
Keyqueries are defined implicitly by the index and the retrieval model of a reference search engine: keyqueries for a document are the minimal queries that return the document in the top result ranks.  ...  Our experiments emphasize the role of the reference search engine and show the potential of keyqueries as innovative document descriptors for large, fast evolving bodies of digital content such as the  ...  TextRank is an unsupervised keyword and keyphrase extraction technique that represents a document as a graph and determines a keyword ranking by applying the PageRank algorithm.  ... 
doi:10.1145/2484028.2484181 dblp:conf/sigir/GollubHMS13 fatcat:4kefpe37brcwdnd7trktwjdg54

METICOS Deliverable D6.2 Social data analysis and extracted perceptions

Sarang Shaikh, Sule Yildirim Yayilgan, Mohamed Abomhara, Erjon Zoto
2022 Zenodo  
Section 5 and 6 discuss the perception extraction from the social media data and review the SoTA studies for perception extraction.  ...  of the automatic border control technologies.  ...  The rules may be both hands crafted from the data available and also can be automatically extracted from data using machine and deep learning techniques.  ... 
doi:10.5281/zenodo.6684365 fatcat:mfb6qkj73zdbbgskruqetubczq

Proceedings of the 3rd International Open Search Symposium #ossym2021 [article]

Andreas Wagner, Michael Granitzer, Christian Guetl, Christine Plote, Voigt Stefan
2022 Zenodo  
Initiative from all relevant scientific, societal, public, and economic domains.  ...  generation of internet search - for the current and future users of an democratic, fair and open Internet – for us all.  ...  ACKNOWLEDGEMENTS This project is made possible by a generous donation from the NLnet Foundation. ACKNOWLEDGEMENTS This project is made possible by a generous grant from the NLnet Foundation.  ... 
doi:10.5281/zenodo.6840911 fatcat:tw5xbexkwjguhoqcyxn5tdvbta

Proceedings of the 3rd International Open Search Symposium #ossym2021 [article]

Andreas Wagner, Michael Granitzer, Christian Guetl, Christine Plote, Voigt Stefan
2022 Zenodo  
Initiative from all relevant scientific, societal, public, and economic domains.  ...  generation of internet search - for the current and future users of an democratic, fair and open Internet – for us all.  ...  ACKNOWLEDGEMENTS This project is made possible by a generous donation from the NLnet Foundation. ACKNOWLEDGEMENTS This project is made possible by a generous grant from the NLnet Foundation.  ... 
doi:10.5281/zenodo.6839942 fatcat:imuoppkmuzdtfnas63ckln4qei

Personalized Scientific Paper Recommendation based on Heterogeneous Graph Representation

Xiao Ma, Ranran Wang
2019 IEEE Access  
A heterogeneous graph representation based recommendation method named HGRec is proposed. First, the author and paper profiles are constructed based on the extracted contents information.  ...  The accelerating rate of scientific publications makes it extremely difficult for researchers to find out the relevant papers and related works.  ...  Inspired by the work of heterogeneous graphs representation [15] , in this paper, we propose a heterogeneous graph representation based personalized scientific paper recommendation method.  ... 
doi:10.1109/access.2019.2923293 fatcat:owaxatica5fd7paux4hgneb5ym

Effective named entity recognition for idiosyncratic web collections

Roman Prokofyev, Gianluca Demartini, Philippe Cudré-Mauroux
2014 Proceedings of the 23rd international conference on World wide web - WWW '14  
We evaluate our system on two test collections created from a set of Computer Science and Physics papers and compare it against state-ofthe-art supervised methods.  ...  We design and evaluate several entity recognition features-ranging from well-known part-of-speech tags to n-gram co-location statistics and decision trees-to classify candidates.  ...  The first components in our pipeline extract text from the input documents and perform some automatic preprocessing (e.g., lemmatization).  ... 
doi:10.1145/2566486.2568013 dblp:conf/www/ProkofyevDC14 fatcat:gdbalfzlsvhfhdmoyoiln6r6zq

Unsupervised Approaches for Textual Semantic Annotation, A Survey

Xiaofeng Liao, Zhiming Zhao
2019 ACM Computing Surveys  
Link to publication Creative Commons License (see https://creativecommons.org/use-remix/cc-licenses): CC BY Citation for published version (APA):  ...  ACKNOWLEDGMENTS The authors thank the anonymous reviewers for their helpful comments, in addition to Cees de Laat, Paul Martin, Jayachander Surbiryala, and ZeShun Shi for useful discussions.  ...  use of keyphrases and topics).  ... 
doi:10.1145/3324473 fatcat:fg5ucwtloze6ljdlh4hqjkqxfe
« Previous Showing results 1 — 15 out of 135 results