Filters








70 Hits in 9.2 sec

Learning to Recommend Descriptive Tags for Questions in Social Forums

Liqiang Nie, Yi-Liang Zhao, Xiangyu Wang, Jialie Shen, Tat-Seng Chua
2014 ACM Transactions on Information Systems  
Extensive evaluations on a representative real-world dataset demonstrate that our scheme yields significant gains for question annotation, and more importantly, the whole process of our approach is unsupervised  ...  Around 40% of the questions in the emerging social-oriented question answering forums have at most one manually labeled tag, which is caused by incomprehensive question understanding or informal tagging  ...  This space is constructed by estimating the semantical similarity score f i between each q i (q i ∈ Q) and q via our proposed adaptive probabilistic hypergraph learning approach.  ... 
doi:10.1145/2559157 fatcat:xnvxabh2yjan5blypnid67ozb4

A Survey on Event Extraction for Natural Language Understanding: Riding the Biomedical Literature Wave

Giacomo Frisoni, Gianluca Moro, Antonella Carbonaro
2021 IEEE Access  
Events can model complex interactions involving multiple participants having a specific semantic role, also handling nested and overlapping definitions.  ...  With the development of deep learning, the granularity of information extraction is evolving from entities and pairwise relations to events.  ...  ACKNOWLEDGMENT The authors thank Giulio Carlassare for his contributions during productive discussions and practical experiments on biomedical corpora.  ... 
doi:10.1109/access.2021.3130956 fatcat:wlr7zeikdva77ojuppqx3vmocy

Message from the general chair

Benjamin C. Lee
2015 2015 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)  
Our system gives a better performance than all the learning-based systems from the CoNLL-2011 shared task on the same dataset.  ...  We propose a joint learning model which combines pairwise classification and mention clustering with Markov logic.  ...  Learning to Find Translations and Transliterations on the Web Joseph Z. Chang, Jason S.  ... 
doi:10.1109/ispass.2015.7095776 dblp:conf/ispass/Lee15 fatcat:ehbed6nl6barfgs6pzwcvwxria

Socializing the Semantic Gap

Xirong Li, Tiberio Uricchio, Lamberto Ballan, Marco Bertini, Cees G. M. Snoek, Alberto Del Bimbo
2016 ACM Computing Surveys  
Where previous reviews on content-based image retrieval emphasize on what can be seen in an image to bridge the semantic gap, this survey considers what people tag about an image.  ...  For a head-to-head comparison between the state-of-the-art, a new experimental protocol is presented, with training sets containing 10k, 100k and 1m images and an evaluation on three test sets, contributed  ...  ACKNOWLEDGMENTS The authors thank Dr. Jitao Sang for providing the TensorAnalysis results, and Dr. Meng Wang and Dr. Yue Gao for making the Flickr51 dataset available for this survey.  ... 
doi:10.1145/2906152 fatcat:ir6obqydirgihlu54pnwy4clny

Time-Frequency Scattering Accurately Models Auditory Similarities Between Instrumental Playing Techniques [article]

Vincent Lostanlen, Christian El-Hajj, Mathias Rossignol, Grégoire Lafay, Joakim Andén, Mathieu Lagrange
2020 arXiv   pre-print
Our model relies on joint time–frequency scattering features to extract spectrotemporal modulations as acoustic features.  ...  In addition, we propose a machine listening model to recover the cluster graph of auditory similarities across instruments, mutes, and techniques.  ...  We also wish to thank the students of the Paris Conservatory and all anonymous participants to our study.  ... 
arXiv:2007.10926v2 fatcat:54efqx4xbvcj5befxjb5ejfhr4

Time–frequency scattering accurately models auditory similarities between instrumental playing techniques

Vincent Lostanlen, Christian El-Hajj, Mathias Rossignol, Grégoire Lafay, Joakim Andén, Mathieu Lagrange
2021 EURASIP Journal on Audio, Speech, and Music Processing  
Our model relies on joint time–frequency scattering features to extract spectrotemporal modulations as acoustic features.  ...  In addition, we propose a machine listening model to recover the cluster graph of auditory similarities across instruments, mutes, and techniques.  ...  We also wish to thank the students of the Paris Conservatory and all anonymous participants to our study.  ... 
doi:10.1186/s13636-020-00187-z pmid:33488686 pmcid:PMC7801324 fatcat:5tmi3yteuffvjcfon5gedecefe

Information Retrieval with Verbose Queries

Manish Gupta, Michael Bendersky
2015 Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval - SIGIR '15  
This survey shows that the work on information retrieval with verbose queries has already produced many valuable insights and significant improvements in the state-of-the-art of the current information  ...  retrieval models.  ...  Finding Related Videos 105 ranked list of top k images. Agrawal et al. [2011] propose two algorithms to solve this problem: Affinity and Comity. Affinity works as follows.  ... 
doi:10.1145/2766462.2767877 dblp:conf/sigir/GuptaB15 fatcat:tgjnvqbbwfepjiggyecfaupqsa

Gravitate Project D3.1 Report On Shape Analysis And Matching And On Semantic Matching

Silvia Biasotti, Andrea Cerri, Chiara Catalano E., Bianca Falcidieno, Maria Laura Torrente, Stuart Middleton E., Leo Dorst, Ilan Shimshoni, Ayellet Tal, Dominic Oldman
2016 Zenodo  
After the review of the current literature on these fields, we end the report with common remarks on possible or plausible cross connections that suggest themselves.  ...  These fields are relatively disjoint, and the research and development challenge of GRAVITATE is precisely to merge them.  ...  These two work represent high level and low level partonomies, with semantic grounding via either expert manual labelling or automatically derived numerical signatures based on 3D scanning data.  ... 
doi:10.5281/zenodo.55432 fatcat:tc3rsykiufezxeper7ldew2ibu

CBSSD: community-based semantic subgroup discovery

Blaž Škrlj, Jan Kralj, Nada Lavrač
2019 Journal of Intelligent Information Systems  
In Section 5 we evaluate the use of the CBSSD approach on ten different life science data sets, i.e. expert defined gene sets, where the CBSSD methodology is quantitatively compared to existing enrichment  ...  Following the idea of multi-view learning, using different sources of information to obtain better models, the CBSSD approach can leverage different types of nodes of the induced complex network, simultaneously  ...  Information Networks for Knowledge Discovery in Life Sciences (J7-7303) and Semantic Data Mining for Linked Open Data (financed under the ERC Complementary Scheme, N2-0078).  ... 
doi:10.1007/s10844-019-00545-0 fatcat:ld4tedsjszcjhdm4xod6t5kvli

From Symbols to Embeddings: A Tale of Two Representations in Computational Social Science

Huimin Chen, Cheng Yang, Xuanming Zhang, Zhiyuan Liu, Maosong Sun, Jianbin Jin
2021 Journal of Social Computing  
Afterwards, we present the applications of the above representations based on the investigation of more than 400 research articles from 6 top venues involved with CSS.  ...  The study of CSS is data-driven and significantly benefits from the availability of online user-generated contents and social networks, which contain rich text and network data for investigation.  ...  Their model could be deep or non-linear, and thus more flexible than the matrix factorization-based ones.  ... 
doi:10.23919/jsc.2021.0011 fatcat:sczl7racpng75agdrddgnrex3q

Structure and dynamics of molecular networks: A novel paradigm of drug discovery

Peter Csermely, Tamás Korcsmáros, Huba J.M. Kiss, Gábor London, Ruth Nussinov
2013 Pharmacology and Therapeutics  
The central hit strategy selectively targets central nodes/edges of the flexible networks of infectious agents or cancer cells to kill them.  ...  Despite considerable progress in genome- and proteome-based high-throughput screening methods and in rational drug design, the increase in approved drugs in the past decade did not match the increase of  ...  colleagues for reading the original version of the paper and for valuable suggestions.  ... 
doi:10.1016/j.pharmthera.2013.01.016 pmid:23384594 pmcid:PMC3647006 fatcat:osjkz6kpr5gzxomqlyenla2fvq

From Symbols to Embeddings: A Tale of Two Representations in Computational Social Science [article]

Huimin Chen, Cheng Yang, Xuanming Zhang, Zhiyuan Liu, Maosong Sun, Jianbin Jin
2021 arXiv   pre-print
Afterwards, we present the applications of the above representations based on the investigation of more than 400 research articles from 6 top venues involved with CSS.  ...  The study of CSS is data-driven and significantly benefits from the availability of online user-generated contents and social networks, which contain rich text and network data for investigation.  ...  Their model could be deep or non-linear, and thus more flexible than the matrix factorization-based ones.  ... 
arXiv:2106.14198v1 fatcat:dvy5awnfuvbnnkzusjl5wbhfki

Applications of Artificial Intelligence in Battling Against Covid-19: A Literature Review

Mohammad-H. Tayarani-N.
2020 Chaos, Solitons & Fractals  
Here, we perform an overview on the applications of AI in a variety of fields including diagnosis of the disease via different types of tests and symptoms, monitoring patients, identifying severity of  ...  We also tried to conclude the paper with ideas on how the problems can be tackled in a better way and provide some suggestions for future works.  ...  Then the uncertainty of the nodes is computed via a measurement and is used as weight in the hypergraph. Finally, a learning process is performed on the hypergraph to predict the new testing cases.  ... 
doi:10.1016/j.chaos.2020.110338 pmid:33041533 pmcid:PMC7532790 fatcat:gl3i37hag5gflajsa7fh6khvva

Learning Neural Textual Representations for Citation Recommendation

Binh Thanh Kieu, Inigo Jauregi Unanue, Son Bao Pham, Hieu Xuan Phan, Massimo Piccardi
2021 2020 25th International Conference on Pattern Recognition (ICPR)  
DAY 2 -Jan 13, 2021 Peng, Tao; Li, Rong; Li, Shang; Zhu, Pengfei 2183 Learning from Web Data: Improving Crowd Counting Via Semi- Supervised Learning DAY 2 -Jan 13, 2021 Kawanishi, Yasutomo  ...  Expertise Modeling for Expert Recommendation DAY 4 -Jan 15, 2021 Dai, Huangpeng; Xie, Qing; Ma, Yanchun; Liu, Yongjian; Xiong, ShengWu 347 RGB-Infrared Person Re-Identification Via Image Modality  ... 
doi:10.1109/icpr48806.2021.9412725 fatcat:3vge2tpd2zf7jcv5btcixnaikm

Recommender Systems [chapter]

Prem Melville, Vikas Sindhwani
2017 Encyclopedia of Machine Learning and Data Mining  
In probabilistic logic learning, two types of semantics are distinguished (De Raedt and Kersting 2003) : the model theoretic semantics and the proof theoretic semantics.  ...  shaping, or model-based reinforcement learning in which the experience is used to learn a domain model, which can then be solved via dynamic programming.  ...  Consequently, the learning algorithms typically differ in the type of search they use for finding these rules in the search space.  ... 
doi:10.1007/978-1-4899-7687-1_964 fatcat:3voghk7xz5cindlgj4pwek7r6u
« Previous Showing results 1 — 15 out of 70 results