423,232 Hits in 3.8 sec

Learning Hierarchies from Ambiguous Natural Language Data [chapter]

Takefumi Yamazaki, Michael J. Pazzani, Christopher Merz
1995 Machine Learning Proceedings 1995  
Acknowledgement We wish to thank Dr. Shigeo Kaneda, Dr. Satoru Ikehara and Dr. Tsukasa Kawaoka for their continuous encouragement of this research.  ...  a hierarchy and are used to generate a hierarchy.  ...  Learning a Semantic Hierarchy from scratch As mentioned above, a semantic hierarchy plays an important role from the view of oering the more general terms needed for generating an appropriate level of  ... 
doi:10.1016/b978-1-55860-377-6.50077-3 dblp:conf/icml/YamazakiPM95 fatcat:vd24rnejfbcrjbxiz3qkuo6uru

Acquiring and updating hierarchical knowledge for machine translation based on a clustering technique [chapter]

Takefumi Yamazaki, Michael J. Pazzani, Christopher Merz
1996 Lecture Notes in Computer Science  
A new hierarchy is then generated by applying a clustering method to internal disjunctions of the learned rules and new rules are learned under the bias of this hierarchy.  ...  When acquiring a hierarchy from scratch, translation rules are learned by an inductive learning algorithm in the rst step.  ...  Acknowledgement We wish to thank Dr. Shigeo Kaneda, Dr. Satoru Ikehara and Dr. Tsukasa Kawaoka for their continuous encouragement of this research.  ... 
doi:10.1007/3-540-60925-3_57 fatcat:plis45r7njh6xhyzcdu4rht7he

Understanding user intention in image retrieval: generalization selection using multiple concept hierarchies

Abdelmadjid Youcefa, Mohammed Lamine Kherfi, Belal Khaldi, Oussama Aiadi
2019 TELKOMNIKA (Telecommunication Computing Electronics and Control)  
This is a very challenging task due to the different interpretations that can be drawn from the same query. To solve such a problem, we introduce a model based on Bayesian generalization.  ...  In addition and instead of using one single concept hierarchy, we propose a generalization so it can be used with multiple hierarchies where each one has a different semantic context and contains several  ...  The main aim in [15] for example was how to learn a new visual category (i.e., generalization) from few positive examples.  ... 
doi:10.12928/telkomnika.v17i5.10202 fatcat:xthx4rxlybhzvew7q5aluxx4ga

Machine Learning of User Profiles: Representational Issues [article]

Eric Bloedorn , Inderjeet Mani, T. Richard MacMillan (MITRE Corporation)
1997 arXiv   pre-print
The research described here focuses on the importance of a suitable generalization hierarchy and representation for learning profiles which are predictively accurate and comprehensible.  ...  Our experiments, conducted in the context of a content-based profiling system for on-line newspapers on the World Wide Web (the IDD News Browser), demonstrate the importance of a generalization hierarchy  ...  The generalization hierarchy, which came to us from TextWise Inc.'s thesaurus consists of three levels.  ... 
arXiv:cmp-lg/9712002v2 fatcat:5a5l6vakdfh45iy76uusxh5yca

RHB+: A Type-Oriented ILP System Learning from Positive Data

Yutaka Sasaki, Masahiko Haruno
1997 International Joint Conference on Artificial Intelligence  
RHB+ makes use of type information to efficiently compute informativity from positive examples only and to judge a stopping condition.  ...  Unfortunately, learning performance is usually poor if types are attached when only positive examples are available.  ...  It helped us improve performance of FOIL and PROGOL in the experiments.  ... 
dblp:conf/ijcai/SasakiH97 fatcat:ljyqqejqizhm5cuhclbvnkbmse

Learning Best Concept Approximations from Examples

Mihai Boicu, Gheorghe Tecuci
2005 International Journal of Computational Intelligence Research  
This paper addresses the problem of learning the best approximation of a concept from examples, when the concept cannot be expressed in the learner's representation language.  ...  This method was developed for the Disciple learning agent that can be taught by a subject matter expert how to perform complex problem solving tasks.  ...  learning from examples [14] , and reduces to it if the target concept C is included in the generalization hierarchy GH.  ... 
doi:10.5019/j.ijcir.2005.27 fatcat:rbeab3favfdqvl6opdinfsqffe

An object-oriented modeling of the history of optimal retrievals

Yong Zhang, Vijay V. Raghavan, Jitender S. Deogun
1991 Proceedings of the 14th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '91  
The ways in which such a hierarchy may be used to retrieve answers to new queries are outlined.  ...  Learning techniques are used in IR to exploit userfeedback in order that the system can improve its peflormance with respect to particular queries.  ...  The clustering algorithm is used to generate a hierarchy of concepts.  ... 
doi:10.1145/122860.122885 dblp:conf/sigir/ZhangRD91 fatcat:6udoagpsqbhqlby36fhdo6a3ai

Conceptual learning in database design

Yannis E. Ionnidis, Tomas Saulys, Andrew J. Whitsitt
1992 ACM Transactions on Information Systems  
A GBM hierarchy is built up by generalizing from sets of examples.  ...  This is crucial because many of the machine learning algorithms that learn from examples do so by making use of both positive and negative examples of a concept.  ... 
doi:10.1145/146760.146779 fatcat:st6l63fcs5ggreluhbydsni7y4

Leveraging Prior Concept Learning Improves Generalization From Few Examples in Computational Models of Human Object Recognition

Joshua S. Rule, Maximilian Riesenhuber
2021 Frontiers in Computational Neuroscience  
We used a benchmark deep learning model to show that the hierarchy can also be leveraged to vastly improve the speed of learning.  ...  These results suggest techniques for learning even more efficiently and provide a biologically plausible way to learn new visual concepts from few examples.  ...  We define the Generic 2 and Generic 3 features using layers from these auxiliary networks that correspond to the layer from the primary classifier used to define Generic 1 .  ... 
doi:10.3389/fncom.2020.586671 pmid:33510629 pmcid:PMC7835122 fatcat:25sn7lntlbcxzl4ef3kfizd5ju

Visual Concept Learning: Combining Machine Vision and Bayesian Generalization on Concept Hierarchies

Yangqing Jia, Joshua T. Abbott, Joseph L. Austerweil, Thomas L. Griffiths, Trevor Darrell
2013 Neural Information Processing Systems  
Current methods typically fail to find the appropriate level of generalization in a concept hierarchy for a given set of visual examples.  ...  Learning a visual concept from a small number of positive examples is a significant challenge for machine learning algorithms.  ...  Bayesian Concept Learning Prior work on concept learning [21] addressed the problem of generalization from examples using a Bayesian framework: given a set of N examples (images in our case) X = {x 1  ... 
dblp:conf/nips/JiaAAGD13 fatcat:k6i36judc5f77jlzcgpc2fmqvm

Learning to Generate Code Comments from Class Hierarchies [article]

Jiyang Zhang, Sheena Panthaplackel, Pengyu Nie, Raymond J. Mooney, Junyi Jessy Li, Milos Gligoric
2021 arXiv   pre-print
Our approach features: (1) incorporating context from the class hierarchy; (2) conditioning on learned, latent representations of specificity to generate comments that capture the more specialized behavior  ...  Our experiments show that the proposed approach is able to generate comments for overriding methods of higher quality compared to prevailing comment generation techniques.  ...  By limiting the number of closely-related examples (i.e, methods from sibling classes) across partitions, this setting allows us to better evaluate a model's ability to generalize.  ... 
arXiv:2103.13426v2 fatcat:5wp7tc3q2nfizau5qhnh4w7h2y

Convolutional Cobweb: A Model of Incremental Learning from 2D Images [article]

Christopher J. MacLellan, Harshil Thakur
2022 arXiv   pre-print
This paper presents a new concept formation approach that supports the ability to incrementally learn and predict labels for visual images.  ...  and use concepts.  ...  We also thank the Drexel University STAR program for providing support for Harshil Thakur to work on this project over the summer term.  ... 
arXiv:2201.06740v1 fatcat:zozjd7gzangapivljhv32gumku

Unsupervised Hierarchical Grouping of Knowledge Graph Entities [article]

Sameh K. Mohamed
2019 arXiv   pre-print
In this work, we propose a new unsupervised approach that learns to categorize entities into a hierarchy of named groups.  ...  We show that our approach is able to effectively learn entity groups using a scalable procedure in noisy and sparse datasets.  ...  We then learn the hierarchy of these groups using intersection and containment ratios between them to build a hierarchy of entity types.  ... 
arXiv:1908.07281v1 fatcat:l4sr3r64dvekfcmi3vk77p7ysq

Multiple Convergence: An Approach to Disjunctive Concept Acquisition

K. S. Murray
1987 International Joint Conference on Artificial Intelligence  
Multiple convergence has been implemented in the learning system HYDRA, and a detailed example of its execution is presented.  ...  conjunction of generalized features.  ...  ACKNOWLEDGEMENTS I would like to thank Joe Ross, Ray Bareiss and especially Bruce Porter for their many insightful and encouraging comments.  ... 
dblp:conf/ijcai/Murray87 fatcat:kp5aznkhazfrbjpgrnronjskki

Language Acquisition: Learning a Hierarchy of Phrases

Uri Zernik
1987 International Joint Conference on Artificial Intelligence  
The hierarchical lexicon, in contrast to the traditional flat lexicon, enables a linguistic model to perform even in situations of incomplete knowledge: when a specific entry is missing, a more general  ...  The Global Hierarchy: A hierarchy is defined, to accommodate for phrases at all levels of generality.  ...  The input required by the algorithm is a sequence of specific episodes, or training examples, from which lexical entries at various levels in the hierarchy arc generalized and specialized.  ... 
dblp:conf/ijcai/Zernick87 fatcat:fmysjaagfre5dalxttnxeugw64
« Previous Showing results 1 — 15 out of 423,232 results