Filters








1,155 Hits in 7.8 sec

Less is Less: When Are Snippets Insufficient for Human vs Machine Relevance Estimation? [article]

Gabriella Kazai, Bhaskar Mitra, Anlei Dong, Nick Craswell, Linjun Yang
2022
This raises questions about when such summaries are sufficient for relevance estimation by the ranking model or the human assessor, and whether humans and machines benefit from the document's full text  ...  Our findings show that the full text is beneficial for humans and a BERT model for similar query and document types, e.g., tail, long queries.  ...  These scenarios motivate us to study when snippets are sufficient replacements of the full body text for relevance estimation by humans and machines.  ... 
doi:10.48550/arxiv.2201.08721 fatcat:fhlqaiwnfvdchlksl44cu5qefq

Mining geographic data for fuel consumption estimation

Vitor Ribeiro, Joao Rodrigues, Ana Aguiar
2013 16th International IEEE Conference on Intelligent Transportation Systems (ITSC 2013)  
In an effort to reduce both emissions and, mostly important, costs, since money is a global motivator, an innovative solution for fuel consumption estimation is proposed, taking advantage of the opportunities  ...  Modern cities possess large and complex transportation networks, whose operating conditions sometimes preclude the minimization of human mobility associated costs, and contribute to an unsustainable growth  ...  values are insufficient [DR02] .  ... 
doi:10.1109/itsc.2013.6728221 dblp:conf/itsc/RibeiroRA13 fatcat:w2raqrd4jvb5ffrgpd7cwipitm

In-IDE Code Generation from Natural Language: Promise and Challenges [article]

Frank F. Xu, Bogdan Vasilescu, Graham Neubig
2021 arXiv   pre-print
One major difficulty of programming is turning concept into code, especially when dealing with the APIs of unfamiliar libraries.  ...  Analysis identifies several pain points that could improve the effectiveness of future machine learning based code generation/retrieval developer assistants, and demonstrates when developers prefer code  ...  We also thank anonymous reviewers for their comments on revising this paper.  ... 
arXiv:2101.11149v3 fatcat:3wyizxvtvnarjehq5koxbesq64

Deep PPG: Large-Scale Heart Rate Estimation with Convolutional Neural Networks

Attila Reiss, Ina Indlekofer, Philip Schmidt, Kristof Van Laerhoven
2019 Sensors  
However, existing approaches are highly parametrised and optimised for specific scenarios of small, public datasets.  ...  Photoplethysmography (PPG)-based continuous heart rate monitoring is essential in a number of domains, e.g., for healthcare or fitness applications.  ...  Acknowledgments: We would like to thank all the study participants for taking part in our data collection user study, thus enabling the creation of the dataset PPG-DaLiA.  ... 
doi:10.3390/s19143079 pmid:31336894 pmcid:PMC6679242 fatcat:7yxsn6hiznfrjpuzksh2y7iabm

On-line topical importance estimation: an effective focused crawling algorithm combining link and content analysis

Can Wang, Zi-yu Guan, Chun Chen, Jia-jun Bu, Jun-feng Wang, Huai-zhong Lin
2009 Journal of Zhejiang University: Science A  
Focused crawling is an important technique for topical resource discovery on the Web.  ...  The key issue in focused crawling is to prioritize uncrawled uniform resource locators (URLs) in the frontier to focus the crawling on relevant pages.  ...  As human efforts are prohibitively large for judging a large number of Web pages, we depend on the three classifiers to make relevance judgment.  ... 
doi:10.1631/jzus.a0820481 fatcat:gpbva4slrjb4rksndd442xmok4

App-Aware Response Synthesis for User Reviews [article]

Umar Farooq, A.B. Siddique, Fuad Jamour, Zhijia Zhao, Vagelis Hristidis
2020 arXiv   pre-print
Given a new user review, it first retrieves the top-K most relevant app reviews and the most relevant snippet from the app description.  ...  The retrieved information and the new user review are then fed into a fused machine learning model that integrates the seq2seq model with a machine reading comprehension model.  ...  ACKNOWLEDGMENT This work is supported in part by the National Science Foundation under grants IIS-1838222 and IIS-1901379.  ... 
arXiv:2007.15793v3 fatcat:5nvwow6zjbdqnm45kb4wceqria

Exploring relevance for clicks

Rongwei Cen, Yiqun Liu, Min Zhang, Bo Zhou, Liyun Ru, Shaoping Ma
2009 Proceeding of the 18th ACM conference on Information and knowledge management - CIKM '09  
A learning algorithm is presented to estimate the quality of user clicks.  ...  Mining feedback information from user click-through data is an important issue for modern Web retrieval systems in terms of architecture analysis, performance evaluation and algorithm optimization.  ...  ROC graphs [8] are commonly used in machine learning and data mining research, especially for quality estimation researches.  ... 
doi:10.1145/1645953.1646246 dblp:conf/cikm/CenLZZRM09 fatcat:l2pb3e7ojjgl7dr74biu22czj4

Trajectons: Action recognition through the motion analysis of tracked features

Pyry Matikainen, Martial Hebert, Rahul Sukthankar
2009 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops  
The defining feature of video compared to still images is motion, and as such the selection of good motion features for action recognition is crucial, especially for bag of words techniques that rely heavily  ...  We present a technique for motion based on quantized trajectory snippets of tracked features.  ...  This idea is consistent with typical bag of words approaches and allows the representation to discriminate between similar types of motion when necessary (e.g., running vs. jogging).  ... 
doi:10.1109/iccvw.2009.5457659 dblp:conf/iccvw/MatikainenHS09 fatcat:zosizmd4mrcyln5cq64dpapgem

Computational Estimation by Scientific Data Mining with Classical Methods to Automate Learning Strategies of Scientists

Aparna S. Varde
2022 ACM Transactions on Knowledge Discovery from Data  
These and other challenges are addressed in this work. The AutoDomainMine approach is used to build a computational estimation system, rigorously evaluated with real data in Materials Science.  ...  Knowledge discovered thereby from a database of existing experiments serves as the basis for estimation.  ...  This is derived as follows in Code Snippet 3.  ... 
doi:10.1145/3502736 fatcat:knjd4iuwxnakbmkx4l6ej3njj4

Tonality Estimation In Electronic Dance Music: A Computational And Musically Informed Examination

Ángel Faraldo, Sergi Jordà, Perfecto Herrera
2018 Zenodo  
This dissertation revolves around the task of computational key estimation in electronic dance music, upon which three interrelated operations are performed.  ...  Based on this corpus, I propose the creation of more open-ended key labels, accounting for other modal practises and ambivalent tonal configurations.  ...  As for the rest of humanity, I only wish this was not done completely in vain. Acknowledgements XV Barcelona, 21 st December, 2017 Ángel Faraldo  ... 
doi:10.5281/zenodo.1154586 fatcat:fqd24dcqlvhflcsluwpja2x4zu

DAiSEE: Towards User Engagement Recognition in the Wild [article]

Abhay Gupta, Arjun D'Cunha, Kamal Awasthi, Vineeth Balasubramanian
2018 arXiv   pre-print
The dataset is available for download at https://iith.ac.in/~daisee-dataset  ...  We introduce DAiSEE, the first multi-label video classification dataset comprising of 9068 video snippets captured from 112 users for recognizing the user affective states of boredom, confusion, engagement  ...  All video snippets with less than 4 annotations are removed, resulting in a dataset with 9,068 snippets and 2,723,882 frames.  ... 
arXiv:1609.01885v6 fatcat:dgbz4gsrovcelhabajawysgm4e

Predicting Human Intentions from Motion Only: A 2D+3D Fusion Approach [article]

Andrea Zunino, Jacopo Cavazza, Atesh Koul, Andrea Cavallo, Cristina Becchio, Vittorio Murino
2017 arXiv   pre-print
There is neuro-psychological evidence that actions performed by humans are anticipated by peculiar motor acts which are discriminant of the type of action going to be performed afterwards.  ...  the context-free prediction of human intents.  ...  Results for the snippet analysis using AlexNet-OF-VLAD features. 2D snippet analysis 20% 40% 60% 80% 100 % Pouring vs. Placing 77.38 87.02 91.43 92.06 94.18 Pouring vs.  ... 
arXiv:1605.09526v4 fatcat:ueqdzsfxnjcrpdsmiuvvisjaie

SCAD

Anton Bakalov, Ariel Fuxman, Partha Pratim Talukdar, Soumen Chakrabarti
2011 Proceedings of the 20th international conference on World wide web - WWW '11  
There is one ILP per entity and it is small enough to be solved in under 38 milliseconds in our experiments.  ...  Similar results are offered in other domains like food, entertainment, travel, etc. All these experiences are fueled by the availability of structured data about the entities of interest.  ...  Notice that there is some chance that 12 vs 11.7 oz. is just precision variation, and both are unstrung weights.  ... 
doi:10.1145/1963405.1963469 dblp:conf/www/BakalovFTC11 fatcat:gf5qyrij5jgefj5yiw6iw3hi7u

Extracting relevance and affect information from physiological text annotation

Oswald Barral, Ilkka Kosunen, Tuukka Ruotsalo, Michiel M. Spapé, Manuel J. A. Eugster, Niklas Ravaja, Samuel Kaski, Giulio Jacucci
2016 User modeling and user-adapted interaction  
Results show that physiological user signals are associated with relevance and affect.  ...  We discuss how our findings help design personalized systems that can annotate digital content using human physiology without the need for any explicit user interaction.  ...  Results show that electrodermal activity is different when users are reading relevant content than when they are reading irrelevant content. Physiological annotation for affect.  ... 
doi:10.1007/s11257-016-9184-8 fatcat:lcvurhgg4ffzxodxmkvr4wbryq

Operational Engines [chapter]

Douglas W. Oard, Carl Madson, Joseph Olive, John McCary, Caitlin Christianson
2011 Handbook of Natural Language Processing and Machine Translation  
But, it is exactly that level at which we must learn to work if we are to learn how best to integrate the diverse language technologies that we are now able to create.  ...  The goal of the GALE Program is to empower the warfighter through the use of language technologies.  ...  We would also like to thank Charles Wayne for his early contributions to the pre-GALE efforts.  ... 
doi:10.1007/978-1-4419-7713-7_6 fatcat:lmrbdpy5sjbkxokmxv4a7vbf74
« Previous Showing results 1 — 15 out of 1,155 results